Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.6083. Min Act: -0.1700
Data Index: 4548923 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.6083. Min Act: -0.1700
Data Index: 4763067 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.6083. Min Act: -0.1700
Data Index: 4145771 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.5761. Min Act: -0.1700
Data Index: 646401 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.5600. Min Act: -0.1700
Data Index: 7232758 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.5115. Min Act: -0.1700
Data Index: 5982757 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.5115. Min Act: -0.1700
Data Index: 3676351 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.5115. Min Act: -0.1700
Data Index: 4281048 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.5115. Min Act: -0.1700
Data Index: 7619564 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4953. Min Act: -0.1700
Data Index: 7537972 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4953. Min Act: -0.1700
Data Index: 7524759 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4953. Min Act: -0.1700
Data Index: 7477639 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4953. Min Act: -0.1700
Data Index: 2601514 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4953. Min Act: -0.1700
Data Index: 5976429 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4791. Min Act: -0.1700
Data Index: 5883790 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4628. Min Act: -0.1700
Data Index: 6227087 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4628. Min Act: -0.1700
Data Index: 2540567 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4791. Min Act: -0.1700
Data Index: 2514998 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4791. Min Act: -0.1700
Data Index: 5612124 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6083. Min Range: -2.6083
Max Act: 2.4628. Min Act: -0.1700
Data Index: 4869608 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19