Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.6703. Min Act: -0.1700
Data Index: 5012530 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.6390. Min Act: -0.1700
Data Index: 7102186 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.6077. Min Act: -0.1700
Data Index: 8272788 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.5920. Min Act: -0.1700
Data Index: 3529810 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.5920. Min Act: -0.1700
Data Index: 2033594 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.5451. Min Act: -0.1700
Data Index: 5558142 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4981. Min Act: -0.1700
Data Index: 7225316 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4981. Min Act: -0.1700
Data Index: 2350240 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4981. Min Act: -0.1700
Data Index: 6052288 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4354. Min Act: -0.1700
Data Index: 2243583 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4354. Min Act: -0.1700
Data Index: 8193877 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4511. Min Act: -0.1700
Data Index: 5134114 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4354. Min Act: -0.1700
Data Index: 8618124 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4197. Min Act: -0.1700
Data Index: 808235 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4197. Min Act: -0.1700
Data Index: 5622782 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4197. Min Act: -0.1700
Data Index: 7814788 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4197. Min Act: -0.1700
Data Index: 8260500 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4197. Min Act: -0.1700
Data Index: 5852931 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4197. Min Act: -0.1700
Data Index: 3312578 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6703. Min Range: -3.6703
Max Act: 3.4041. Min Act: -0.1700
Data Index: 4746306 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19