Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.3277. Min Act: -0.1700
Data Index: 5355272 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.2965. Min Act: -0.1700
Data Index: 8681157 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.2652. Min Act: -0.1700
Data Index: 7378250 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.2652. Min Act: -0.1700
Data Index: 6721319 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.2652. Min Act: -0.1700
Data Index: 8595873 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.1402. Min Act: -0.1700
Data Index: 5884206 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.1402. Min Act: -0.1700
Data Index: 4432964 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.1090. Min Act: -0.1700
Data Index: 2037062 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.1090. Min Act: -0.1700
Data Index: 57355 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.0465. Min Act: -0.1700
Data Index: 4224758 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.0465. Min Act: -0.1700
Data Index: 5061704 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.0465. Min Act: -0.1700
Data Index: 2715402 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.0465. Min Act: -0.1700
Data Index: 135188 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.0465. Min Act: -0.1700
Data Index: 720739 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.0152. Min Act: -0.1700
Data Index: 8177261 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3277. Min Range: -7.3277
Max Act: 7.0152. Min Act: -0.1700
Data Index: 8568749 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3277. Min Range: -7.3277
Max Act: 6.9527. Min Act: -0.1700
Data Index: 3382150 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3277. Min Range: -7.3277
Max Act: 6.9527. Min Act: -0.1700
Data Index: 7377910 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3277. Min Range: -7.3277
Max Act: 6.9840. Min Act: -0.1700
Data Index: 3533669 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3277. Min Range: -7.3277
Max Act: 6.9527. Min Act: -0.1700
Data Index: 5634766 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19