Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0702. Min Range: -12.0702
Max Act: 12.0702. Min Act: -0.1700
Data Index: 3062804 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0702. Min Range: -12.0702
Max Act: 12.0702. Min Act: -0.1695
Data Index: 8142894 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.8202. Min Act: -0.1699
Data Index: 7018892 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.6327. Min Act: -0.1700
Data Index: 8633708 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.6327. Min Act: -0.1700
Data Index: 1332469 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.5077. Min Act: -0.1700
Data Index: 8009705 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.3827. Min Act: -0.1696
Data Index: 8437450 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.3827. Min Act: -0.1700
Data Index: 916495 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.3202. Min Act: -0.1700
Data Index: 8774365 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.3202. Min Act: -0.1700
Data Index: 6611497 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.1952. Min Act: -0.1700
Data Index: 529618 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.2577. Min Act: -0.1700
Data Index: 3880177 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.1952. Min Act: -0.1700
Data Index: 7227276 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.1952. Min Act: -0.1700
Data Index: 4753776 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.1327. Min Act: -0.1700
Data Index: 8496718 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.1327. Min Act: -0.1700
Data Index: 5399501 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.1327. Min Act: -0.1681
Data Index: 1639547 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.0702. Min Act: -0.1687
Data Index: 5966420 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.0702. Min Act: -0.1700
Data Index: 4647121 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0702. Min Range: -12.0702
Max Act: 11.0077. Min Act: -0.1700
Data Index: 8044809 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19