Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2172. Min Range: -8.2172
Max Act: 8.2172. Min Act: -0.1700
Data Index: 1893682 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2172. Min Range: -8.2172
Max Act: 8.2172. Min Act: -0.1700
Data Index: 3683572 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2172. Min Range: -8.2172
Max Act: 8.1547. Min Act: -0.1700
Data Index: 2475895 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2172. Min Range: -8.2172
Max Act: 8.0922. Min Act: -0.1700
Data Index: 7147561 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2172. Min Range: -8.2172
Max Act: 8.0297. Min Act: -0.1700
Data Index: 5137418 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2172. Min Range: -8.2172
Max Act: 8.0297. Min Act: -0.1700
Data Index: 5364221 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2172. Min Range: -8.2172
Max Act: 8.0297. Min Act: -0.1700
Data Index: 6459158 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.9672. Min Act: -0.1700
Data Index: 2496250 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.9672. Min Act: -0.1700
Data Index: 6032826 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.9672. Min Act: -0.1700
Data Index: 7194211 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.9672. Min Act: -0.1700
Data Index: 7713939 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.9047. Min Act: -0.1700
Data Index: 7764669 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.9047. Min Act: -0.1700
Data Index: 2475894 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.8422. Min Act: -0.1697
Data Index: 269868 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.9047. Min Act: -0.1700
Data Index: 4976209 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.8422. Min Act: -0.1700
Data Index: 2693359 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.8422. Min Act: -0.1700
Data Index: 1271265 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.8422. Min Act: -0.1700
Data Index: 8432963 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.7797. Min Act: -0.1700
Data Index: 2082529 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2172. Min Range: -8.2172
Max Act: 7.7797. Min Act: -0.1700
Data Index: 7506214 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19