Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.7464. Min Act: -0.1700
Data Index: 5940318 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.7464. Min Act: -0.1700
Data Index: 3147922 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.6214. Min Act: -0.1700
Data Index: 5732020 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.7464. Min Act: -0.1700
Data Index: 1257787 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.5901. Min Act: -0.1700
Data Index: 6466869 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.5276. Min Act: -0.1700
Data Index: 5643456 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.6214. Min Act: -0.1700
Data Index: 2705081 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.4964. Min Act: -0.1700
Data Index: 5489849 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.4339. Min Act: -0.1700
Data Index: 3895320 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.4026. Min Act: -0.1700
Data Index: 7194935 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.4026. Min Act: -0.1700
Data Index: 2122735 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.4964. Min Act: -0.1700
Data Index: 4752594 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.4339. Min Act: -0.1700
Data Index: 6317474 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.4964. Min Act: -0.1700
Data Index: 4236138 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.3089. Min Act: -0.1700
Data Index: 55724 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.3714. Min Act: -0.1700
Data Index: 8161048 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.3089. Min Act: -0.1700
Data Index: 8825433 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.2776. Min Act: -0.1700
Data Index: 4472827 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.3401. Min Act: -0.1700
Data Index: 117564 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7464. Min Range: -7.7464
Max Act: 7.4339. Min Act: -0.1700
Data Index: 3147586 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19