Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6479069 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.6443. Min Act: -0.1700
Data Index: 4947238 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.5506. Min Act: -0.1700
Data Index: 4834393 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.4881. Min Act: -0.1700
Data Index: 3708108 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.4568. Min Act: -0.1700
Data Index: 3708106 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.4568. Min Act: -0.1700
Data Index: 3221429 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.4255. Min Act: -0.1700
Data Index: 4947237 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3943. Min Act: -0.1700
Data Index: 3506709 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3630. Min Act: -0.1700
Data Index: 1837257 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3943. Min Act: -0.1700
Data Index: 5271388 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3630. Min Act: -0.1700
Data Index: 46607 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3630. Min Act: -0.1700
Data Index: 8321412 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3630. Min Act: -0.1700
Data Index: 5637187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3630. Min Act: -0.1700
Data Index: 1957056 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3318. Min Act: -0.1700
Data Index: 2492029 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3318. Min Act: -0.1700
Data Index: 401394 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3318. Min Act: -0.1700
Data Index: 1126568 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3005. Min Act: -0.1700
Data Index: 5859678 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3005. Min Act: -0.1700
Data Index: 4618272 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6756. Min Range: -4.6756
Max Act: 4.3318. Min Act: -0.1700
Data Index: 2345504 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19