Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4704 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2695. Min Range: -5.2695
Max Act: 5.2695. Min Act: -0.1700
Data Index: 8331266 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2695. Min Range: -5.2695
Max Act: 5.1445. Min Act: -0.1700
Data Index: 1390978 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.9882. Min Act: -0.1700
Data Index: 8676791 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.9570. Min Act: -0.1700
Data Index: 8583901 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.9257. Min Act: -0.1700
Data Index: 1259583 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.8945. Min Act: -0.1700
Data Index: 7011388 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.8945. Min Act: -0.1700
Data Index: 4694294 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.8945. Min Act: -0.1700
Data Index: 4728815 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.8320. Min Act: -0.1700
Data Index: 4253161 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.7382. Min Act: -0.1700
Data Index: 3493359 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.7070. Min Act: -0.1700
Data Index: 1154413 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.6757. Min Act: -0.1700
Data Index: 4689453 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.7382. Min Act: -0.1700
Data Index: 287295 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.6757. Min Act: -0.1700
Data Index: 4260395 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.6757. Min Act: -0.1700
Data Index: 4875011 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 6228541 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 1928520 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 713780 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 3284429 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2695. Min Range: -5.2695
Max Act: 4.6445. Min Act: -0.1700
Data Index: 7661551 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19