Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4264 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.5177. Min Act: -0.1700
Data Index: 1062568 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.2825. Min Act: -0.1700
Data Index: 854593 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.2354. Min Act: -0.1700
Data Index: 8776021 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.1725. Min Act: -0.1700
Data Index: 4869626 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.1410. Min Act: -0.1700
Data Index: 5763059 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.1095. Min Act: -0.1700
Data Index: 1644364 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.1252. Min Act: -0.1700
Data Index: 1588898 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0937. Min Act: -0.1700
Data Index: 2362339 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0780. Min Act: -0.1700
Data Index: 6158844 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0780. Min Act: -0.1700
Data Index: 1625780 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0780. Min Act: -0.1700
Data Index: 2712777 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0622. Min Act: -0.1700
Data Index: 5113766 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0622. Min Act: -0.1700
Data Index: 4550858 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0464. Min Act: -0.1700
Data Index: 4819995 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0464. Min Act: -0.1700
Data Index: 6078174 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0622. Min Act: -0.1700
Data Index: 7792159 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0464. Min Act: -0.1700
Data Index: 6869980 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0306. Min Act: -0.1700
Data Index: 8536594 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.0148. Min Act: -0.1700
Data Index: 8137905 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5177. Min Range: -3.5177
Max Act: 2.9990. Min Act: -0.1700
Data Index: 3518834 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19