Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2154. Min Range: -7.2154
Max Act: 7.2154. Min Act: -0.1700
Data Index: 5890401 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.9654. Min Act: -0.1700
Data Index: 1701829 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.7467. Min Act: -0.1700
Data Index: 5421083 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.7154. Min Act: -0.1700
Data Index: 7383371 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.7154. Min Act: -0.1700
Data Index: 1239481 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.7154. Min Act: -0.1700
Data Index: 6226077 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.6529. Min Act: -0.1700
Data Index: 533256 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.6529. Min Act: -0.1700
Data Index: 4220615 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.6529. Min Act: -0.1700
Data Index: 2746083 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.6217. Min Act: -0.1700
Data Index: 1549665 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.6217. Min Act: -0.1700
Data Index: 2609530 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.6217. Min Act: -0.1700
Data Index: 4572363 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.5592. Min Act: -0.1700
Data Index: 1343619 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.5904. Min Act: -0.1700
Data Index: 4661986 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.5279. Min Act: -0.1700
Data Index: 8012314 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.5279. Min Act: -0.1700
Data Index: 7081089 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.4967. Min Act: -0.1700
Data Index: 5677402 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.4967. Min Act: -0.1700
Data Index: 7509007 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.4967. Min Act: -0.1700
Data Index: 7089303 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2154. Min Range: -7.2154
Max Act: 6.4967. Min Act: -0.1700
Data Index: 7098435 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19