Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.5927. Min Act: -0.1700
Data Index: 2728366 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.5766. Min Act: -0.1700
Data Index: 2731301 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.5443. Min Act: -0.1700
Data Index: 2566443 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4958. Min Act: -0.1700
Data Index: 5471084 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4958. Min Act: -0.1700
Data Index: 3029197 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4958. Min Act: -0.1700
Data Index: 1450258 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4471. Min Act: -0.1700
Data Index: 1682778 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4308. Min Act: -0.1700
Data Index: 3026161 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4471. Min Act: -0.1700
Data Index: 8770635 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.3982. Min Act: -0.1700
Data Index: 4379125 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.3982. Min Act: -0.1700
Data Index: 1329268 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4145. Min Act: -0.1700
Data Index: 2019872 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.3819. Min Act: -0.1700
Data Index: 5551240 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.3982. Min Act: -0.1700
Data Index: 463085 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4308. Min Act: -0.1700
Data Index: 7233927 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.3982. Min Act: -0.1700
Data Index: 547500 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.3982. Min Act: -0.1700
Data Index: 5893320 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.3982. Min Act: -0.1700
Data Index: 8196134 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.3982. Min Act: -0.1700
Data Index: 2123880 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5927. Min Range: -2.5927
Max Act: 2.4145. Min Act: -0.1700
Data Index: 8439584 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19