Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1587 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.4932. Min Act: -0.1700
Data Index: 6075656 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.4932. Min Act: -0.1700
Data Index: 6785918 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.5244. Min Act: -0.1700
Data Index: 5951008 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.5244. Min Act: -0.1700
Data Index: 4374299 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.5244. Min Act: -0.1700
Data Index: 2832439 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3994. Min Act: -0.1700
Data Index: 1938136 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3994. Min Act: -0.1700
Data Index: 7119758 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3994. Min Act: -0.1700
Data Index: 7947427 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3994. Min Act: -0.1700
Data Index: 4969213 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3682. Min Act: -0.1700
Data Index: 2694958 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3994. Min Act: -0.1700
Data Index: 1062086 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3682. Min Act: -0.1700
Data Index: 557100 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3057. Min Act: -0.1700
Data Index: 466609 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3369. Min Act: -0.1700
Data Index: 7999536 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3369. Min Act: -0.1700
Data Index: 1041702 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3057. Min Act: -0.1700
Data Index: 1504784 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3057. Min Act: -0.1700
Data Index: 3356787 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3057. Min Act: -0.1700
Data Index: 152360 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.3057. Min Act: -0.1700
Data Index: 643103 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5244. Min Range: -5.5244
Max Act: 5.2744. Min Act: -0.1700
Data Index: 6595470 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19