Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.9208. Min Act: -0.1700
Data Index: 1957819 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.8270. Min Act: -0.1700
Data Index: 2397073 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7958. Min Act: -0.1700
Data Index: 3355023 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7645. Min Act: -0.1700
Data Index: 787826 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7333. Min Act: -0.1700
Data Index: 2775950 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7333. Min Act: -0.1700
Data Index: 4950150 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7333. Min Act: -0.1700
Data Index: 5333223 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7333. Min Act: -0.1700
Data Index: 3143918 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7645. Min Act: -0.1700
Data Index: 7519186 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 2128439 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 3482388 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 3091783 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 7159583 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 6549594 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 6357584 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 4415244 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 4070864 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6708. Min Act: -0.1700
Data Index: 2161318 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7020. Min Act: -0.1700
Data Index: 4030557 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6708. Min Act: -0.1700
Data Index: 799831 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19