Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3472. Min Range: -1.3472
Max Act: 1.3472. Min Act: -0.1687
Data Index: 8752176 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.9874. Min Act: -0.1491
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3472. Min Range: -1.3472
Max Act: 1.1358. Min Act: -0.1696
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.9701. Min Act: -0.1700
Data Index: 8752172 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.7249. Min Act: -0.1700
Data Index: 5713040 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.4592. Min Act: -0.1683
Data Index: 4993227 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.6198. Min Act: -0.1700
Data Index: 948006 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.6040. Min Act: -0.1688
Data Index: 3862348 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.6040. Min Act: -0.1696
Data Index: 3599447 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5961. Min Act: -0.1607
Data Index: 380410 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5571. Min Act: -0.1700
Data Index: 5587887 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5571. Min Act: -0.1700
Data Index: 4346112 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5649. Min Act: -0.1700
Data Index: 5433532 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5418. Min Act: -0.1700
Data Index: 7000148 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5494. Min Act: -0.1698
Data Index: 1588412 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5418. Min Act: -0.1700
Data Index: 1933323 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5418. Min Act: -0.1700
Data Index: 1933317 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5494. Min Act: -0.1700
Data Index: 8066452 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5571. Min Act: -0.1700
Data Index: 2910547 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3472. Min Range: -1.3472
Max Act: 0.5341. Min Act: -0.1696
Data Index: 3482790 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19