Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1950 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4967. Min Act: -0.1700
Data Index: 526494 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4967. Min Act: -0.1700
Data Index: 3455257 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4967. Min Act: -0.1700
Data Index: 5183602 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4342. Min Act: -0.1700
Data Index: 7377578 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4654. Min Act: -0.1700
Data Index: 2839229 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4654. Min Act: -0.1700
Data Index: 3334680 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.4654. Min Act: -0.1700
Data Index: 8788871 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3717. Min Act: -0.1700
Data Index: 172321 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3717. Min Act: -0.1700
Data Index: 7902738 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3717. Min Act: -0.1700
Data Index: 4560997 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3717. Min Act: -0.1700
Data Index: 4035101 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3717. Min Act: -0.1700
Data Index: 784389 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3717. Min Act: -0.1700
Data Index: 3697855 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3092. Min Act: -0.1700
Data Index: 7828881 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3717. Min Act: -0.1700
Data Index: 6533718 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3404. Min Act: -0.1700
Data Index: 1859389 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3717. Min Act: -0.1700
Data Index: 5616550 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3404. Min Act: -0.1700
Data Index: 7170855 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.2779. Min Act: -0.1700
Data Index: 1918685 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4967. Min Range: -5.4967
Max Act: 5.3092. Min Act: -0.1700
Data Index: 2921843 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19