Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1325 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3802. Min Range: -8.3802
Max Act: 8.3802. Min Act: -0.1700
Data Index: 7341269 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3802. Min Range: -8.3802
Max Act: 8.1927. Min Act: -0.1700
Data Index: 8121620 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.8802. Min Act: -0.1700
Data Index: 1570692 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.8177. Min Act: -0.1700
Data Index: 1462925 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.7552. Min Act: -0.1700
Data Index: 2436127 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.7552. Min Act: -0.1700
Data Index: 8022488 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.6302. Min Act: -0.1700
Data Index: 4353500 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.6927. Min Act: -0.1700
Data Index: 949081 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.6302. Min Act: -0.1700
Data Index: 839207 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.6302. Min Act: -0.1700
Data Index: 824552 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.6302. Min Act: -0.1700
Data Index: 5402058 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.6302. Min Act: -0.1700
Data Index: 4048256 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.5677. Min Act: -0.1700
Data Index: 910579 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.5677. Min Act: -0.1700
Data Index: 4040323 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.5677. Min Act: -0.1700
Data Index: 8313555 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.5677. Min Act: -0.1700
Data Index: 3158658 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.5677. Min Act: -0.1700
Data Index: 1585552 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.5052. Min Act: -0.1700
Data Index: 8696112 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.5052. Min Act: -0.1700
Data Index: 92681 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3802. Min Range: -8.3802
Max Act: 7.4739. Min Act: -0.1700
Data Index: 2840628 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19