Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.8297. Min Act: -0.1700
Data Index: 7619650 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.6734. Min Act: -0.1700
Data Index: 4046731 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.6109. Min Act: -0.1700
Data Index: 8061130 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.5172. Min Act: -0.1700
Data Index: 2854192 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.5172. Min Act: -0.1700
Data Index: 5642637 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.5172. Min Act: -0.1700
Data Index: 6391903 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.5172. Min Act: -0.1700
Data Index: 99202 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4859. Min Act: -0.1700
Data Index: 7932444 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4547. Min Act: -0.1700
Data Index: 4656630 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4547. Min Act: -0.1700
Data Index: 6965617 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4547. Min Act: -0.1700
Data Index: 4871907 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4547. Min Act: -0.1700
Data Index: 5429709 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4547. Min Act: -0.1700
Data Index: 5281676 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4234. Min Act: -0.1700
Data Index: 2771026 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4234. Min Act: -0.1700
Data Index: 4347593 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4234. Min Act: -0.1700
Data Index: 2784265 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.3922. Min Act: -0.1700
Data Index: 2496046 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4234. Min Act: -0.1700
Data Index: 8516996 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.4234. Min Act: -0.1700
Data Index: 3392929 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8297. Min Range: -5.8297
Max Act: 5.3922. Min Act: -0.1700
Data Index: 7251480 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19