Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.6645. Min Act: -0.1700
Data Index: 2228525 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.4457. Min Act: -0.1700
Data Index: 2671928 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.4145. Min Act: -0.1700
Data Index: 2124595 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.3832. Min Act: -0.1700
Data Index: 6197052 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.3520. Min Act: -0.1700
Data Index: 8033659 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.3207. Min Act: -0.1700
Data Index: 8166814 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.2895. Min Act: -0.1700
Data Index: 2803903 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.2582. Min Act: -0.1700
Data Index: 6562285 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.2270. Min Act: -0.1700
Data Index: 2482095 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.2582. Min Act: -0.1700
Data Index: 6852785 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.2270. Min Act: -0.1700
Data Index: 7473565 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.1957. Min Act: -0.1700
Data Index: 7261915 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.1957. Min Act: -0.1700
Data Index: 7521812 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.2270. Min Act: -0.1700
Data Index: 5161756 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.2270. Min Act: -0.1700
Data Index: 3386939 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.1957. Min Act: -0.1700
Data Index: 1550824 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.1957. Min Act: -0.1700
Data Index: 8715959 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.1957. Min Act: -0.1700
Data Index: 1132633 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.1957. Min Act: -0.1700
Data Index: 544726 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6645. Min Range: -6.6645
Max Act: 6.1332. Min Act: -0.1700
Data Index: 4849532 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19