Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.8049. Min Act: -0.1700
Data Index: 3884384 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.6799. Min Act: -0.1700
Data Index: 7419104 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.6487. Min Act: -0.1700
Data Index: 4117005 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.6487. Min Act: -0.1700
Data Index: 7419121 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.6174. Min Act: -0.1700
Data Index: 2743403 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5862. Min Act: -0.1700
Data Index: 492916 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5862. Min Act: -0.1700
Data Index: 7532369 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5862. Min Act: -0.1700
Data Index: 8384416 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5549. Min Act: -0.1700
Data Index: 1394682 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5549. Min Act: -0.1700
Data Index: 5922188 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5862. Min Act: -0.1700
Data Index: 3481391 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5237. Min Act: -0.1700
Data Index: 2036561 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5237. Min Act: -0.1700
Data Index: 7140591 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5237. Min Act: -0.1700
Data Index: 7052412 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5237. Min Act: -0.1700
Data Index: 7140592 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.5549. Min Act: -0.1700
Data Index: 6781518 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.4924. Min Act: -0.1700
Data Index: 7140589 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.4612. Min Act: -0.1699
Data Index: 6393385 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.4924. Min Act: -0.1700
Data Index: 7140586 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8049. Min Range: -4.8049
Max Act: 4.4924. Min Act: -0.1700
Data Index: 686919 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19