Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4204 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.7836. Min Act: -0.1700
Data Index: 6449475 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.5961. Min Act: -0.1700
Data Index: 4104355 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.5649. Min Act: -0.1700
Data Index: 317124 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.5336. Min Act: -0.1700
Data Index: 2732741 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.5336. Min Act: -0.1700
Data Index: 5335589 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.5336. Min Act: -0.1700
Data Index: 1926977 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4711. Min Act: -0.1700
Data Index: 7538482 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4399. Min Act: -0.1700
Data Index: 8009384 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4399. Min Act: -0.1700
Data Index: 2641083 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4086. Min Act: -0.1700
Data Index: 507011 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4086. Min Act: -0.1700
Data Index: 5573188 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4086. Min Act: -0.1700
Data Index: 1797167 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4086. Min Act: -0.1700
Data Index: 1733976 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4399. Min Act: -0.1700
Data Index: 7820986 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4086. Min Act: -0.1699
Data Index: 5100124 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4086. Min Act: -0.1700
Data Index: 3932012 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4086. Min Act: -0.1700
Data Index: 4734139 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.4086. Min Act: -0.1700
Data Index: 430107 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.3461. Min Act: -0.1700
Data Index: 4623861 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7836. Min Range: -5.7836
Max Act: 5.3774. Min Act: -0.1700
Data Index: 6038860 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19