Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4220 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.9655. Min Act: -0.1700
Data Index: 1751891 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.9343. Min Act: -0.1700
Data Index: 6984597 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.9030. Min Act: -0.1700
Data Index: 2301095 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.9030. Min Act: -0.1700
Data Index: 3860245 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.8405. Min Act: -0.1700
Data Index: 2289656 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.8405. Min Act: -0.1700
Data Index: 2198262 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7780. Min Act: -0.1700
Data Index: 7854771 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7468. Min Act: -0.1700
Data Index: 5368132 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7468. Min Act: -0.1700
Data Index: 2038313 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7155. Min Act: -0.1700
Data Index: 2949684 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7468. Min Act: -0.1700
Data Index: 169920 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7155. Min Act: -0.1700
Data Index: 422653 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7155. Min Act: -0.1700
Data Index: 294777 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7468. Min Act: -0.1699
Data Index: 6850909 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7155. Min Act: -0.1700
Data Index: 2180120 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7155. Min Act: -0.1700
Data Index: 1446156 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.7155. Min Act: -0.1700
Data Index: 7439430 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.6530. Min Act: -0.1700
Data Index: 4865407 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.6530. Min Act: -0.1700
Data Index: 581514 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9655. Min Range: -5.9655
Max Act: 5.6530. Min Act: -0.1700
Data Index: 1411804 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19