Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2902. Min Act: -0.1700
Data Index: 7618090 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2902. Min Act: -0.1700
Data Index: 5452158 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2590. Min Act: -0.1700
Data Index: 5882769 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2590. Min Act: -0.1700
Data Index: 2003596 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2277. Min Act: -0.1700
Data Index: 5901798 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2277. Min Act: -0.1700
Data Index: 6055314 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2277. Min Act: -0.1700
Data Index: 7520836 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2277. Min Act: -0.1700
Data Index: 2738238 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2277. Min Act: -0.1700
Data Index: 8347816 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2277. Min Act: -0.1700
Data Index: 8563062 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2277. Min Act: -0.1700
Data Index: 4870944 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.2277. Min Act: -0.1700
Data Index: 842630 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.1964. Min Act: -0.1700
Data Index: 4982111 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.1964. Min Act: -0.1700
Data Index: 2325728 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.1964. Min Act: -0.1700
Data Index: 2293089 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.1964. Min Act: -0.1700
Data Index: 4850636 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.1964. Min Act: -0.1700
Data Index: 4760805 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.1964. Min Act: -0.1700
Data Index: 316437 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.1964. Min Act: -0.1700
Data Index: 4532770 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2902. Min Range: -4.2902
Max Act: 4.1964. Min Act: -0.1700
Data Index: 3215135 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19