Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.3493. Min Act: -0.1700
Data Index: 5830953 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.3181. Min Act: -0.1700
Data Index: 6764755 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2868. Min Act: -0.1700
Data Index: 7960030 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2556. Min Act: -0.1700
Data Index: 4011630 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2556. Min Act: -0.1700
Data Index: 2287330 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2556. Min Act: -0.1700
Data Index: 3190060 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2556. Min Act: -0.1700
Data Index: 2665489 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 7188538 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2556. Min Act: -0.1700
Data Index: 1426665 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 76095 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.1931. Min Act: -0.1700
Data Index: 5470948 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.1931. Min Act: -0.1700
Data Index: 4890383 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 1945963 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.1931. Min Act: -0.1700
Data Index: 8093428 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.1931. Min Act: -0.1700
Data Index: 8750237 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 2819355 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.1306. Min Act: -0.1700
Data Index: 5747667 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.1931. Min Act: -0.1700
Data Index: 6556979 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.1306. Min Act: -0.1700
Data Index: 1995251 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3493. Min Range: -6.3493
Max Act: 6.1618. Min Act: -0.1700
Data Index: 3239345 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19