Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4201 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.8542. Min Act: -0.1700
Data Index: 4571314 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.6980. Min Act: -0.1700
Data Index: 4104904 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.6667. Min Act: -0.1700
Data Index: 646036 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.5417. Min Act: -0.1700
Data Index: 2475212 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.5105. Min Act: -0.1700
Data Index: 5678418 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.5105. Min Act: -0.1700
Data Index: 4951256 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.4792. Min Act: -0.1700
Data Index: 3254990 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.4167. Min Act: -0.1700
Data Index: 283301 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.4480. Min Act: -0.1700
Data Index: 7418948 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.4167. Min Act: -0.1700
Data Index: 2877534 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3854. Min Act: -0.1700
Data Index: 3548615 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3854. Min Act: -0.1700
Data Index: 3332116 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3854. Min Act: -0.1700
Data Index: 2839286 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3854. Min Act: -0.1700
Data Index: 8143687 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3854. Min Act: -0.1700
Data Index: 5713773 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3854. Min Act: -0.1700
Data Index: 8430859 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3854. Min Act: -0.1700
Data Index: 3121052 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3542. Min Act: -0.1700
Data Index: 3454258 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.3542. Min Act: -0.1700
Data Index: 2928999 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8542. Min Range: -4.8542
Max Act: 4.2917. Min Act: -0.1700
Data Index: 4815353 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19