Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6019 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1639. Min Act: -0.1700
Data Index: 4532472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1639. Min Act: -0.1700
Data Index: 2451011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1639. Min Act: -0.1700
Data Index: 5574490 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1327. Min Act: -0.1700
Data Index: 7820935 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1327. Min Act: -0.1700
Data Index: 7741616 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 8500427 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 7037785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 6846169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 6184095 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 3820448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 13536 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 2337482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 6615921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 683810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 1554559 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 6795177 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 2228417 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 821642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 3092341 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 48414 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19