Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0507. Min Range: -7.0507
Max Act: 7.0507. Min Act: -0.1700
Data Index: 4592200 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.8007. Min Act: -0.1700
Data Index: 5358381 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.6444. Min Act: -0.1700
Data Index: 4849673 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.7069. Min Act: -0.1700
Data Index: 6395669 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.6444. Min Act: -0.1700
Data Index: 7081962 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.5819. Min Act: -0.1700
Data Index: 1758129 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.5819. Min Act: -0.1700
Data Index: 8647177 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.5194. Min Act: -0.1700
Data Index: 3416837 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.4257. Min Act: -0.1700
Data Index: 2340300 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.4569. Min Act: -0.1700
Data Index: 6418843 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.4569. Min Act: -0.1700
Data Index: 4921655 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.3944. Min Act: -0.1700
Data Index: 2866876 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.4257. Min Act: -0.1700
Data Index: 4516700 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.3944. Min Act: -0.1700
Data Index: 8070608 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.3007. Min Act: -0.1700
Data Index: 4342560 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.3319. Min Act: -0.1700
Data Index: 2331788 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.3007. Min Act: -0.1700
Data Index: 1286708 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.3007. Min Act: -0.1700
Data Index: 365431 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.2694. Min Act: -0.1700
Data Index: 1413235 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0507. Min Range: -7.0507
Max Act: 6.3319. Min Act: -0.1700
Data Index: 6115818 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19