Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.8172. Min Act: -0.1700
Data Index: 4384068 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.7859. Min Act: -0.1700
Data Index: 1321301 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.7547. Min Act: -0.1700
Data Index: 59480 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.5359. Min Act: -0.1700
Data Index: 6004092 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.5672. Min Act: -0.1700
Data Index: 3390157 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.5047. Min Act: -0.1700
Data Index: 624679 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.5047. Min Act: -0.1700
Data Index: 6437450 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.4734. Min Act: -0.1700
Data Index: 2256194 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.4734. Min Act: -0.1700
Data Index: 4632207 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.4109. Min Act: -0.1700
Data Index: 6479107 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.4109. Min Act: -0.1700
Data Index: 2929315 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.3797. Min Act: -0.1700
Data Index: 7741331 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.3797. Min Act: -0.1700
Data Index: 178777 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.3797. Min Act: -0.1700
Data Index: 5724254 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.3797. Min Act: -0.1700
Data Index: 1942216 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.4109. Min Act: -0.1700
Data Index: 7292647 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.4109. Min Act: -0.1700
Data Index: 3565527 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.3797. Min Act: -0.1700
Data Index: 8382967 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.3797. Min Act: -0.1700
Data Index: 3029639 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8172. Min Range: -5.8172
Max Act: 5.3797. Min Act: -0.1700
Data Index: 3181183 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19