Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 917 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0511. Min Range: -2.0511
Max Act: 2.0343. Min Act: -0.1700
Data Index: 2191101 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0511. Min Range: -2.0511
Max Act: 2.0511. Min Act: -0.1697
Data Index: 5106206 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0511. Min Range: -2.0511
Max Act: 2.0343. Min Act: -0.1700
Data Index: 276823 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0511. Min Range: -2.0511
Max Act: 2.0174. Min Act: -0.1700
Data Index: 5260277 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0511. Min Range: -2.0511
Max Act: 2.0174. Min Act: -0.1700
Data Index: 8633557 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0511. Min Range: -2.0511
Max Act: 2.0006. Min Act: -0.1700
Data Index: 4969926 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9837. Min Act: -0.1700
Data Index: 3089344 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9837. Min Act: -0.1700
Data Index: 2944160 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9837. Min Act: -0.1674
Data Index: 1326506 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9667. Min Act: -0.1700
Data Index: 6098053 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9667. Min Act: -0.1700
Data Index: 1176364 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9667. Min Act: -0.1700
Data Index: 2489487 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9667. Min Act: -0.1700
Data Index: 7700816 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9497. Min Act: -0.1686
Data Index: 5906760 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9497. Min Act: -0.1700
Data Index: 6600432 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9328. Min Act: -0.1700
Data Index: 3151463 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9157. Min Act: -0.1700
Data Index: 7907267 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9328. Min Act: -0.1700
Data Index: 5410690 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.9157. Min Act: -0.1700
Data Index: 4230591 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0511. Min Range: -2.0511
Max Act: 1.8987. Min Act: -0.1700
Data Index: 1165259 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19