Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4176 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.8481. Min Act: -0.1700
Data Index: 7058732 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.7543. Min Act: -0.1700
Data Index: 2694151 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.6293. Min Act: -0.1700
Data Index: 5204427 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5981. Min Act: -0.1700
Data Index: 3095614 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5668. Min Act: -0.1700
Data Index: 4117778 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5668. Min Act: -0.1700
Data Index: 5640954 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5668. Min Act: -0.1700
Data Index: 8330031 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5668. Min Act: -0.1700
Data Index: 3843653 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5668. Min Act: -0.1700
Data Index: 4894044 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5356. Min Act: -0.1700
Data Index: 5034696 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5668. Min Act: -0.1700
Data Index: 6887147 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5356. Min Act: -0.1700
Data Index: 6909796 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5356. Min Act: -0.1700
Data Index: 6452039 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5356. Min Act: -0.1700
Data Index: 3901921 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5668. Min Act: -0.1700
Data Index: 3585069 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5043. Min Act: -0.1700
Data Index: 6368150 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5356. Min Act: -0.1700
Data Index: 1957001 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5043. Min Act: -0.1700
Data Index: 6335315 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5043. Min Act: -0.1700
Data Index: 1160706 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8481. Min Range: -6.8481
Max Act: 6.5043. Min Act: -0.1700
Data Index: 2885055 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19