Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 330 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0727. Min Range: -7.0727
Max Act: 7.0727. Min Act: -0.1700
Data Index: 1286389 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.9790. Min Act: -0.1700
Data Index: 7165474 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.9477. Min Act: -0.1700
Data Index: 6426273 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.9165. Min Act: -0.1700
Data Index: 3265691 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.8227. Min Act: -0.1700
Data Index: 7159944 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.7915. Min Act: -0.1700
Data Index: 3781148 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.7602. Min Act: -0.1700
Data Index: 693091 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.7602. Min Act: -0.1700
Data Index: 3162422 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.7602. Min Act: -0.1700
Data Index: 4428865 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.7602. Min Act: -0.1700
Data Index: 5022997 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.7290. Min Act: -0.1700
Data Index: 1998946 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.7290. Min Act: -0.1700
Data Index: 1168510 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.6977. Min Act: -0.1700
Data Index: 1959049 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.7290. Min Act: -0.1700
Data Index: 8487009 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.6977. Min Act: -0.1700
Data Index: 7165478 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.6352. Min Act: -0.1700
Data Index: 7956088 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.6352. Min Act: -0.1700
Data Index: 5140274 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.6352. Min Act: -0.1700
Data Index: 4889097 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.6040. Min Act: -0.1700
Data Index: 2812900 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0727. Min Range: -7.0727
Max Act: 6.6040. Min Act: -0.1700
Data Index: 4889098 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19