Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0965. Min Range: -9.0965
Max Act: 9.0965. Min Act: -0.1700
Data Index: 2124822 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0965. Min Range: -9.0965
Max Act: 9.0965. Min Act: -0.1700
Data Index: 4419329 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0965. Min Range: -9.0965
Max Act: 9.0965. Min Act: -0.1700
Data Index: 5108764 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0965. Min Range: -9.0965
Max Act: 9.0340. Min Act: -0.1700
Data Index: 2359031 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.9090. Min Act: -0.1700
Data Index: 4253700 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.9090. Min Act: -0.1700
Data Index: 7063421 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.8465. Min Act: -0.1700
Data Index: 3779390 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.7840. Min Act: -0.1700
Data Index: 7292745 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.7840. Min Act: -0.1700
Data Index: 5991133 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.7840. Min Act: -0.1700
Data Index: 5448064 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.7215. Min Act: -0.1700
Data Index: 6611978 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.7215. Min Act: -0.1700
Data Index: 2940378 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.7840. Min Act: -0.1700
Data Index: 255245 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.6590. Min Act: -0.1700
Data Index: 2669417 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.6590. Min Act: -0.1700
Data Index: 4467412 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.6590. Min Act: -0.1700
Data Index: 3460920 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.6590. Min Act: -0.1700
Data Index: 2262516 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.6590. Min Act: -0.1700
Data Index: 1232367 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.5965. Min Act: -0.1700
Data Index: 1985840 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0965. Min Range: -9.0965
Max Act: 8.5965. Min Act: -0.1700
Data Index: 2811776 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19