Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.2952. Min Act: -0.1700
Data Index: 423929 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.2014. Min Act: -0.1700
Data Index: 4622363 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.1389. Min Act: -0.1700
Data Index: 7744165 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.1077. Min Act: -0.1700
Data Index: 4081654 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.0764. Min Act: -0.1700
Data Index: 1682701 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.0764. Min Act: -0.1700
Data Index: 6520791 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.0764. Min Act: -0.1700
Data Index: 7660281 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.0452. Min Act: -0.1700
Data Index: 2449038 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2952. Min Range: -6.2952
Max Act: 6.0452. Min Act: -0.1700
Data Index: 7721299 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9827. Min Act: -0.1700
Data Index: 4073191 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9827. Min Act: -0.1700
Data Index: 6142727 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9827. Min Act: -0.1700
Data Index: 4185180 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9827. Min Act: -0.1700
Data Index: 841221 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9514. Min Act: -0.1700
Data Index: 953323 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9202. Min Act: -0.1700
Data Index: 7828786 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9202. Min Act: -0.1700
Data Index: 1805354 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9514. Min Act: -0.1700
Data Index: 2294300 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9514. Min Act: -0.1700
Data Index: 210152 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9202. Min Act: -0.1700
Data Index: 3045520 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2952. Min Range: -6.2952
Max Act: 5.9202. Min Act: -0.1700
Data Index: 2307174 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19