Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5591 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.9943. Min Act: -0.1700
Data Index: 7945999 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.5568. Min Act: -0.1700
Data Index: 4477998 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.4318. Min Act: -0.1700
Data Index: 3464241 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.3693. Min Act: -0.1700
Data Index: 4453915 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.2443. Min Act: -0.1700
Data Index: 6426692 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.1193. Min Act: -0.1700
Data Index: 4714897 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.1193. Min Act: -0.1700
Data Index: 8119728 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.1193. Min Act: -0.1700
Data Index: 4481722 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.0568. Min Act: -0.1700
Data Index: 777690 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9943. Min Range: -8.9943
Max Act: 8.1193. Min Act: -0.1700
Data Index: 7388310 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9943. Min Act: -0.1700
Data Index: 1553575 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9943. Min Act: -0.1700
Data Index: 6865603 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9318. Min Act: -0.1700
Data Index: 2536202 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.8693. Min Act: -0.1700
Data Index: 2873294 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9318. Min Act: -0.1700
Data Index: 4650705 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9318. Min Act: -0.1700
Data Index: 8046016 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9318. Min Act: -0.1700
Data Index: 3531561 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9318. Min Act: -0.1700
Data Index: 4844420 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9318. Min Act: -0.1700
Data Index: 6740151 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9943. Min Range: -8.9943
Max Act: 7.9318. Min Act: -0.1700
Data Index: 3280360 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19