Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5052. Min Range: -7.5052
Max Act: 7.5052. Min Act: -0.1700
Data Index: 308287 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.7240. Min Act: -0.1700
Data Index: 1536980 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.6302. Min Act: -0.1700
Data Index: 4287921 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.5677. Min Act: -0.1700
Data Index: 1085062 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.5365. Min Act: -0.1700
Data Index: 6250846 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.5052. Min Act: -0.1700
Data Index: 1922249 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.4427. Min Act: -0.1700
Data Index: 5688087 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.4115. Min Act: -0.1700
Data Index: 7940048 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.3802. Min Act: -0.1700
Data Index: 6004753 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.4115. Min Act: -0.1700
Data Index: 7550279 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.3177. Min Act: -0.1700
Data Index: 2012948 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.3177. Min Act: -0.1700
Data Index: 7339072 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.3177. Min Act: -0.1700
Data Index: 3537877 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.2865. Min Act: -0.1700
Data Index: 1238457 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.2865. Min Act: -0.1700
Data Index: 7550267 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.2865. Min Act: -0.1700
Data Index: 6885673 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.2552. Min Act: -0.1700
Data Index: 5036386 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.1927. Min Act: -0.1700
Data Index: 7583917 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.1927. Min Act: -0.1700
Data Index: 4663223 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5052. Min Range: -7.5052
Max Act: 6.1927. Min Act: -0.1700
Data Index: 6331157 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19