Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2127 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.9943. Min Act: -0.1700
Data Index: 4026673 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.9318. Min Act: -0.1700
Data Index: 6825598 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.9005. Min Act: -0.1700
Data Index: 344751 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.9005. Min Act: -0.1700
Data Index: 687248 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.9005. Min Act: -0.1700
Data Index: 8538488 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.9005. Min Act: -0.1700
Data Index: 4646885 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.9005. Min Act: -0.1700
Data Index: 2756271 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.9005. Min Act: -0.1700
Data Index: 5652590 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8693. Min Act: -0.1700
Data Index: 2436707 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8693. Min Act: -0.1700
Data Index: 5833540 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8693. Min Act: -0.1700
Data Index: 7080334 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8380. Min Act: -0.1700
Data Index: 3746131 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8380. Min Act: -0.1700
Data Index: 4132757 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8380. Min Act: -0.1700
Data Index: 5486365 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8380. Min Act: -0.1700
Data Index: 57929 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8068. Min Act: -0.1700
Data Index: 7983518 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8068. Min Act: -0.1700
Data Index: 5956724 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8068. Min Act: -0.1700
Data Index: 2296517 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8068. Min Act: -0.1700
Data Index: 6292832 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9943. Min Range: -4.9943
Max Act: 4.8068. Min Act: -0.1700
Data Index: 1014020 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19