Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3948 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.4956. Min Act: -0.1700
Data Index: 8571818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.2456. Min Act: -0.1700
Data Index: 1590792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.1831. Min Act: -0.1700
Data Index: 3658996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 7567983 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.1206. Min Act: -0.1695
Data Index: 447345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 6830360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1698
Data Index: 6054995 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 6023826 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 2236698 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 5585261 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 5482165 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1693
Data Index: 5167108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 4991888 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 4660346 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1668
Data Index: 3972691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 340954 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 230902 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 3740618 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 3700858 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4956. Min Range: -7.4956
Max Act: 7.0581. Min Act: -0.1700
Data Index: 3700860 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19