Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3867 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4943. Min Act: -0.1700
Data Index: 3631283 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4943. Min Act: -0.1700
Data Index: 7850114 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 2276553 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 3531339 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 3021229 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 2833197 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 2693850 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 2101047 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 7609653 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 7216196 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 6303181 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 928388 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 5347242 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 4908242 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4631. Min Act: -0.1700
Data Index: 3885498 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 2536553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 2591191 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 1292173 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 2954799 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 2992799 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19