Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.7921. Min Act: -0.1700
Data Index: 1029452 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.7057. Min Act: -0.1700
Data Index: 1974533 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.6884. Min Act: -0.1700
Data Index: 4650934 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.6536. Min Act: -0.1700
Data Index: 5789587 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.6362. Min Act: -0.1690
Data Index: 3855413 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.6362. Min Act: -0.1699
Data Index: 3498792 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.6188. Min Act: -0.1700
Data Index: 8725133 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.6013. Min Act: -0.1700
Data Index: 4283531 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.6188. Min Act: -0.1688
Data Index: 3421644 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5838. Min Act: -0.1700
Data Index: 3761088 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5838. Min Act: -0.1700
Data Index: 5333722 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5838. Min Act: -0.1696
Data Index: 1059494 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5838. Min Act: -0.1700
Data Index: 210513 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5664. Min Act: -0.1700
Data Index: 1074292 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5664. Min Act: -0.1700
Data Index: 1159659 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5313. Min Act: -0.1700
Data Index: 1780260 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5313. Min Act: -0.1700
Data Index: 5656790 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5313. Min Act: -0.1697
Data Index: 2705731 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5138. Min Act: -0.1700
Data Index: 4600126 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7921. Min Range: -1.7921
Max Act: 1.5138. Min Act: -0.1700
Data Index: 6963111 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19