Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3173. Min Range: -9.3173
Max Act: 9.3173. Min Act: -0.1700
Data Index: 4079381 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3173. Min Range: -9.3173
Max Act: 9.1923. Min Act: -0.1700
Data Index: 5378901 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.9423. Min Act: -0.1700
Data Index: 4578623 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.8798. Min Act: -0.1700
Data Index: 3918215 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.8798. Min Act: -0.1700
Data Index: 680828 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.8173. Min Act: -0.1700
Data Index: 7016275 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.7548. Min Act: -0.1700
Data Index: 2255609 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.6923. Min Act: -0.1700
Data Index: 965045 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.6298. Min Act: -0.1700
Data Index: 5733034 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.5048. Min Act: -0.1700
Data Index: 4078065 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.5048. Min Act: -0.1700
Data Index: 4727886 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.5048. Min Act: -0.1700
Data Index: 3225638 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.5048. Min Act: -0.1700
Data Index: 527793 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.4423. Min Act: -0.1700
Data Index: 7450772 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.4423. Min Act: -0.1700
Data Index: 7502245 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.4423. Min Act: -0.1700
Data Index: 4271890 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.4423. Min Act: -0.1700
Data Index: 7586350 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.4423. Min Act: -0.1700
Data Index: 1737536 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.4423. Min Act: -0.1700
Data Index: 6708177 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3173. Min Range: -9.3173
Max Act: 8.3798. Min Act: -0.1700
Data Index: 2767961 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19