Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 461 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.7709. Min Act: -0.1700
Data Index: 8054703 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6458. Min Act: -0.1700
Data Index: 1288260 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6458. Min Act: -0.1700
Data Index: 1739631 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 6015126 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 5296249 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 4711278 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 4570017 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 4275427 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 745980 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 452712 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5832. Min Act: -0.1700
Data Index: 8433461 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 7850157 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 239677 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 2544079 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6145. Min Act: -0.1700
Data Index: 1118376 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5832. Min Act: -0.1700
Data Index: 717668 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5832. Min Act: -0.1700
Data Index: 1887212 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5832. Min Act: -0.1700
Data Index: 4033190 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5832. Min Act: -0.1700
Data Index: 753238 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5832. Min Act: -0.1700
Data Index: 2301617 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19