Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3005. Min Range: -6.3005
Max Act: 6.3005. Min Act: -0.1700
Data Index: 8567519 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3005. Min Range: -6.3005
Max Act: 6.1130. Min Act: -0.1700
Data Index: 876985 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3005. Min Range: -6.3005
Max Act: 6.0818. Min Act: -0.1700
Data Index: 5951932 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3005. Min Range: -6.3005
Max Act: 6.0193. Min Act: -0.1700
Data Index: 2147628 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9880. Min Act: -0.1700
Data Index: 1884281 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9880. Min Act: -0.1700
Data Index: 2129971 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9880. Min Act: -0.1700
Data Index: 6215095 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9880. Min Act: -0.1700
Data Index: 1624953 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7009382 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9880. Min Act: -0.1700
Data Index: 8691261 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9255. Min Act: -0.1700
Data Index: 6362902 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9255. Min Act: -0.1700
Data Index: 2950284 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8943. Min Act: -0.1700
Data Index: 6066288 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8943. Min Act: -0.1700
Data Index: 5644427 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8943. Min Act: -0.1700
Data Index: 7554885 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8630. Min Act: -0.1700
Data Index: 4484185 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8630. Min Act: -0.1700
Data Index: 6639154 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8318. Min Act: -0.1700
Data Index: 2917154 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8318. Min Act: -0.1700
Data Index: 5189958 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8318. Min Act: -0.1700
Data Index: 5273836 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19