Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5629. Min Act: -0.1700
Data Index: 4547315 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5541. Min Act: -0.1700
Data Index: 6023817 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5453. Min Act: -0.1699
Data Index: 7612290 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5541. Min Act: -0.1700
Data Index: 5426072 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5453. Min Act: -0.1700
Data Index: 1615957 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5366. Min Act: -0.1696
Data Index: 273978 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5278. Min Act: -0.1700
Data Index: 7185904 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5366. Min Act: -0.1700
Data Index: 1204145 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5278. Min Act: -0.1699
Data Index: 8090622 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5278. Min Act: -0.1698
Data Index: 8801140 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5278. Min Act: -0.1700
Data Index: 1947706 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5190. Min Act: -0.1697
Data Index: 174938 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5103. Min Act: -0.1700
Data Index: 6767599 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5190. Min Act: -0.1700
Data Index: 5429736 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5103. Min Act: -0.1700
Data Index: 2475064 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5015. Min Act: -0.1700
Data Index: 3332006 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5103. Min Act: -0.1700
Data Index: 1690080 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.4927. Min Act: -0.1700
Data Index: 4062184 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.5015. Min Act: -0.1700
Data Index: 6277671 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5629. Min Range: -1.5629
Max Act: 1.4927. Min Act: -0.1675
Data Index: 6715216 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19