Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.9849. Min Act: -0.1700
Data Index: 4459207 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.7036. Min Act: -0.1700
Data Index: 6643238 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.6099. Min Act: -0.1700
Data Index: 1426610 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.5474. Min Act: -0.1700
Data Index: 3658792 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.5474. Min Act: -0.1700
Data Index: 7358655 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.5474. Min Act: -0.1700
Data Index: 7809365 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.4536. Min Act: -0.1700
Data Index: 3334746 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.4536. Min Act: -0.1700
Data Index: 4534656 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.4536. Min Act: -0.1700
Data Index: 5095431 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.4224. Min Act: -0.1700
Data Index: 7423318 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.4224. Min Act: -0.1700
Data Index: 627187 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.3911. Min Act: -0.1700
Data Index: 744329 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.3911. Min Act: -0.1700
Data Index: 5465828 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.3911. Min Act: -0.1700
Data Index: 1567837 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.3911. Min Act: -0.1700
Data Index: 5393961 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.4224. Min Act: -0.1700
Data Index: 2596042 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.3599. Min Act: -0.1700
Data Index: 3723776 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.3911. Min Act: -0.1700
Data Index: 2609903 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.3599. Min Act: -0.1700
Data Index: 816021 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9849. Min Range: -4.9849
Max Act: 4.3286. Min Act: -0.1700
Data Index: 1152941 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19