Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2544 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3474. Min Range: -7.3474
Max Act: 7.3474. Min Act: -0.1700
Data Index: 1983871 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.7224. Min Act: -0.1700
Data Index: 3051230 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.7224. Min Act: -0.1700
Data Index: 8397157 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.6911. Min Act: -0.1700
Data Index: 81406 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.5349. Min Act: -0.1700
Data Index: 3615571 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.4724. Min Act: -0.1700
Data Index: 7252434 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.4724. Min Act: -0.1700
Data Index: 4075157 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.4724. Min Act: -0.1700
Data Index: 4664350 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.5036. Min Act: -0.1700
Data Index: 6625913 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.4411. Min Act: -0.1700
Data Index: 4551440 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.4411. Min Act: -0.1700
Data Index: 2118268 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.4099. Min Act: -0.1700
Data Index: 1023929 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.3474. Min Act: -0.1700
Data Index: 910458 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.3786. Min Act: -0.1700
Data Index: 1569736 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.2849. Min Act: -0.1700
Data Index: 3002205 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.3161. Min Act: -0.1700
Data Index: 2761875 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.3786. Min Act: -0.1700
Data Index: 845531 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.3161. Min Act: -0.1700
Data Index: 3098805 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.2849. Min Act: -0.1700
Data Index: 7658066 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3474. Min Range: -7.3474
Max Act: 6.3161. Min Act: -0.1700
Data Index: 5362758 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19