Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2130 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.8052. Min Act: -0.1700
Data Index: 3826986 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.8052. Min Act: -0.1700
Data Index: 3062770 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7893. Min Act: -0.1700
Data Index: 4446117 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7734. Min Act: -0.1700
Data Index: 7527269 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7574. Min Act: -0.1700
Data Index: 4797794 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7574. Min Act: -0.1700
Data Index: 2228413 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7415. Min Act: -0.1700
Data Index: 3805502 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7415. Min Act: -0.1700
Data Index: 3400555 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7415. Min Act: -0.1700
Data Index: 5826446 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7255. Min Act: -0.1700
Data Index: 115684 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7255. Min Act: -0.1700
Data Index: 2639739 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7255. Min Act: -0.1700
Data Index: 3722068 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7255. Min Act: -0.1700
Data Index: 2577114 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7095. Min Act: -0.1700
Data Index: 6607791 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7095. Min Act: -0.1700
Data Index: 1490926 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7095. Min Act: -0.1700
Data Index: 6694161 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7095. Min Act: -0.1700
Data Index: 5173706 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7095. Min Act: -0.1657
Data Index: 1490925 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7095. Min Act: -0.1700
Data Index: 1303309 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8052. Min Range: -2.8052
Max Act: 2.7095. Min Act: -0.1700
Data Index: 3176632 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19