Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4752 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.5033. Min Act: -0.1700
Data Index: 1278406 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.4096. Min Act: -0.1700
Data Index: 402163 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.3158. Min Act: -0.1700
Data Index: 8348042 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.1596. Min Act: -0.1700
Data Index: 5828120 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.1283. Min Act: -0.1700
Data Index: 2656456 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.1283. Min Act: -0.1700
Data Index: 8454966 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.0971. Min Act: -0.1700
Data Index: 6517410 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.0971. Min Act: -0.1700
Data Index: 4082886 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.0346. Min Act: -0.1700
Data Index: 4074141 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.0346. Min Act: -0.1700
Data Index: 1683330 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5033. Min Range: -7.5033
Max Act: 7.0033. Min Act: -0.1700
Data Index: 4516208 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.9721. Min Act: -0.1700
Data Index: 4104150 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.9096. Min Act: -0.1700
Data Index: 2586656 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.9096. Min Act: -0.1700
Data Index: 86402 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.8783. Min Act: -0.1700
Data Index: 7258387 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.8783. Min Act: -0.1700
Data Index: 1183007 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.9096. Min Act: -0.1700
Data Index: 1694216 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.8783. Min Act: -0.1700
Data Index: 8467420 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.8471. Min Act: -0.1700
Data Index: 3247286 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5033. Min Range: -7.5033
Max Act: 6.8158. Min Act: -0.1700
Data Index: 3703039 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19