Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8986. Min Range: -7.8986
Max Act: 7.8986. Min Act: -0.1700
Data Index: 3224180 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.9924. Min Act: -0.1700
Data Index: 8293423 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.8361. Min Act: -0.1700
Data Index: 3162287 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.8049. Min Act: -0.1700
Data Index: 3033233 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.7736. Min Act: -0.1700
Data Index: 912628 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.7424. Min Act: -0.1700
Data Index: 8552180 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.7424. Min Act: -0.1700
Data Index: 4044008 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.6799. Min Act: -0.1700
Data Index: 4515652 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.7111. Min Act: -0.1700
Data Index: 7672412 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.6486. Min Act: -0.1700
Data Index: 5301214 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.6174. Min Act: -0.1700
Data Index: 2490496 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.5861. Min Act: -0.1700
Data Index: 203075 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.5549. Min Act: -0.1700
Data Index: 2542164 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.5549. Min Act: -0.1700
Data Index: 1274434 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.5549. Min Act: -0.1700
Data Index: 1452684 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.5549. Min Act: -0.1700
Data Index: 7830162 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.5549. Min Act: -0.1700
Data Index: 7321001 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.5549. Min Act: -0.1700
Data Index: 148133 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.5236. Min Act: -0.1700
Data Index: 5363860 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8986. Min Range: -7.8986
Max Act: 6.4924. Min Act: -0.1700
Data Index: 5154767 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19