Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1162 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.6004. Min Act: -0.1700
Data Index: 5304467 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.5379. Min Act: -0.1700
Data Index: 130161 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.4129. Min Act: -0.1700
Data Index: 3135308 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.3504. Min Act: -0.1700
Data Index: 7867038 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.3504. Min Act: -0.1700
Data Index: 1287899 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.3504. Min Act: -0.1700
Data Index: 2748135 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.3504. Min Act: -0.1700
Data Index: 849848 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.2879. Min Act: -0.1700
Data Index: 3574801 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.2254. Min Act: -0.1700
Data Index: 6920824 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.2879. Min Act: -0.1700
Data Index: 3852099 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.2254. Min Act: -0.1700
Data Index: 7414247 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.2254. Min Act: -0.1700
Data Index: 5740464 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.2254. Min Act: -0.1700
Data Index: 2693673 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.1629. Min Act: -0.1700
Data Index: 1201454 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.1629. Min Act: -0.1700
Data Index: 3708973 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.0379. Min Act: -0.1700
Data Index: 5643899 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.1004. Min Act: -0.1700
Data Index: 1140710 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.1004. Min Act: -0.1700
Data Index: 3528685 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.1004. Min Act: -0.1700
Data Index: 4086689 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6004. Min Range: -8.6004
Max Act: 8.1004. Min Act: -0.1700
Data Index: 4426058 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19