Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4466 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1864. Min Range: -7.1864
Max Act: 7.1864. Min Act: -0.1700
Data Index: 3546394 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.6864. Min Act: -0.1700
Data Index: 8694792 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.6239. Min Act: -0.1700
Data Index: 8200007 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.4989. Min Act: -0.1700
Data Index: 6929100 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.4677. Min Act: -0.1700
Data Index: 4354748 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.5302. Min Act: -0.1700
Data Index: 2084428 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.4677. Min Act: -0.1700
Data Index: 8460621 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.4677. Min Act: -0.1700
Data Index: 3439933 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.4677. Min Act: -0.1700
Data Index: 8108992 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.4052. Min Act: -0.1700
Data Index: 6929101 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3739. Min Act: -0.1700
Data Index: 4392025 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3739. Min Act: -0.1700
Data Index: 7009547 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3427. Min Act: -0.1700
Data Index: 4960632 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3427. Min Act: -0.1700
Data Index: 3186760 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3427. Min Act: -0.1700
Data Index: 3238671 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3427. Min Act: -0.1700
Data Index: 2707687 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3114. Min Act: -0.1700
Data Index: 2409656 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3427. Min Act: -0.1700
Data Index: 3676439 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.3114. Min Act: -0.1700
Data Index: 928116 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1864. Min Range: -7.1864
Max Act: 6.2802. Min Act: -0.1700
Data Index: 1528161 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19