Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0969. Min Range: -7.0969
Max Act: 7.0969. Min Act: -0.1700
Data Index: 1308323 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.6594. Min Act: -0.1700
Data Index: 631460 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.6594. Min Act: -0.1700
Data Index: 6917415 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.6282. Min Act: -0.1700
Data Index: 1189839 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.5969. Min Act: -0.1700
Data Index: 1173147 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.5657. Min Act: -0.1700
Data Index: 7366284 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.5657. Min Act: -0.1700
Data Index: 3325288 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.5344. Min Act: -0.1700
Data Index: 3980043 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.4407. Min Act: -0.1700
Data Index: 4499714 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.4407. Min Act: -0.1700
Data Index: 822434 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.4094. Min Act: -0.1700
Data Index: 5218655 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.4094. Min Act: -0.1700
Data Index: 8777160 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.3782. Min Act: -0.1700
Data Index: 3948184 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.3469. Min Act: -0.1700
Data Index: 630497 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.3157. Min Act: -0.1700
Data Index: 7360091 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.3469. Min Act: -0.1700
Data Index: 429737 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.3157. Min Act: -0.1700
Data Index: 8491406 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.3157. Min Act: -0.1700
Data Index: 2471270 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.3157. Min Act: -0.1700
Data Index: 420328 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0969. Min Range: -7.0969
Max Act: 6.2844. Min Act: -0.1700
Data Index: 6819346 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19