Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0178. Min Range: -4.0178
Max Act: 4.0178. Min Act: -0.1700
Data Index: 7610080 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.9865. Min Act: -0.1700
Data Index: 1066985 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.8615. Min Act: -0.1700
Data Index: 528317 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.8302. Min Act: -0.1700
Data Index: 4374792 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.7520. Min Act: -0.1700
Data Index: 6333800 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.7364. Min Act: -0.1700
Data Index: 4204447 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.7520. Min Act: -0.1700
Data Index: 2219645 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.7051. Min Act: -0.1700
Data Index: 4888309 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.7051. Min Act: -0.1700
Data Index: 5594945 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.7051. Min Act: -0.1700
Data Index: 5478659 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.6582. Min Act: -0.1700
Data Index: 7958329 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.6582. Min Act: -0.1700
Data Index: 1372369 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.6425. Min Act: -0.1700
Data Index: 1169117 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.6112. Min Act: -0.1700
Data Index: 8212326 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.5643. Min Act: -0.1700
Data Index: 7043673 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.6112. Min Act: -0.1700
Data Index: 4525500 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.5956. Min Act: -0.1700
Data Index: 1722004 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.5799. Min Act: -0.1700
Data Index: 7205138 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.5643. Min Act: -0.1700
Data Index: 5635659 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0178. Min Range: -4.0178
Max Act: 3.5643. Min Act: -0.1700
Data Index: 2884481 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19