Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.8494. Min Act: -0.1700
Data Index: 5632826 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.7869. Min Act: -0.1700
Data Index: 8648561 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.5994. Min Act: -0.1700
Data Index: 385077 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.5369. Min Act: -0.1700
Data Index: 929341 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.4744. Min Act: -0.1700
Data Index: 5404958 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.4744. Min Act: -0.1700
Data Index: 3750361 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.3806. Min Act: -0.1700
Data Index: 8728637 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.3181. Min Act: -0.1700
Data Index: 1319195 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.3181. Min Act: -0.1700
Data Index: 7521548 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.2869. Min Act: -0.1700
Data Index: 7034106 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.2556. Min Act: -0.1700
Data Index: 4123369 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.2556. Min Act: -0.1700
Data Index: 4499151 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.2869. Min Act: -0.1700
Data Index: 650769 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.2556. Min Act: -0.1700
Data Index: 8299802 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.1931. Min Act: -0.1700
Data Index: 3200020 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.1931. Min Act: -0.1700
Data Index: 3793314 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.1931. Min Act: -0.1700
Data Index: 6510131 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.1931. Min Act: -0.1700
Data Index: 2712039 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.1619. Min Act: -0.1700
Data Index: 5714645 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8494. Min Range: -7.8494
Max Act: 7.1619. Min Act: -0.1700
Data Index: 6415403 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19