Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4891 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3997. Min Range: -3.3997
Max Act: 3.3997. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.6565. Min Act: -0.1700
Data Index: 8449689 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.5761. Min Act: -0.1700
Data Index: 1718494 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.5276. Min Act: -0.1700
Data Index: 1849702 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4790. Min Act: -0.1700
Data Index: 544428 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4952. Min Act: -0.1700
Data Index: 7436350 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4790. Min Act: -0.1700
Data Index: 4033889 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4790. Min Act: -0.1700
Data Index: 2988669 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4303. Min Act: -0.1700
Data Index: 5609430 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4628. Min Act: -0.1700
Data Index: 2272173 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4303. Min Act: -0.1700
Data Index: 3352587 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4303. Min Act: -0.1700
Data Index: 4372591 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4465. Min Act: -0.1700
Data Index: 6459450 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4628. Min Act: -0.1700
Data Index: 4411314 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4465. Min Act: -0.1700
Data Index: 5381055 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4303. Min Act: -0.1700
Data Index: 3741509 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4465. Min Act: -0.1700
Data Index: 5023 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4303. Min Act: -0.1700
Data Index: 1952897 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4303. Min Act: -0.1700
Data Index: 3993133 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3997. Min Range: -3.3997
Max Act: 2.4303. Min Act: -0.1700
Data Index: 1470615 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19