Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3942 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.2776. Min Act: -0.1700
Data Index: 5085288 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.2463. Min Act: -0.1700
Data Index: 3273701 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.0901. Min Act: -0.1700
Data Index: 7453584 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.0901. Min Act: -0.1700
Data Index: 3394695 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.0588. Min Act: -0.1700
Data Index: 6211023 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2776. Min Range: -4.2776
Max Act: 4.0276. Min Act: -0.1700
Data Index: 4503717 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9963. Min Act: -0.1700
Data Index: 8654305 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9963. Min Act: -0.1700
Data Index: 1540806 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9650. Min Act: -0.1700
Data Index: 1604314 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9650. Min Act: -0.1700
Data Index: 2220778 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9963. Min Act: -0.1700
Data Index: 4334836 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9963. Min Act: -0.1700
Data Index: 6052 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9025. Min Act: -0.1700
Data Index: 1466832 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9338. Min Act: -0.1700
Data Index: 957466 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9338. Min Act: -0.1700
Data Index: 6615541 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9338. Min Act: -0.1700
Data Index: 3789945 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9338. Min Act: -0.1700
Data Index: 4555187 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9338. Min Act: -0.1700
Data Index: 465973 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9338. Min Act: -0.1700
Data Index: 3389303 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2776. Min Range: -4.2776
Max Act: 3.9025. Min Act: -0.1700
Data Index: 7359532 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19