Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 652 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.4374. Min Act: -0.1700
Data Index: 1990765 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.4061. Min Act: -0.1700
Data Index: 7125266 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.4061. Min Act: -0.1700
Data Index: 1090821 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3749. Min Act: -0.1700
Data Index: 7148624 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3749. Min Act: -0.1700
Data Index: 3747751 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3749. Min Act: -0.1700
Data Index: 6300854 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3436. Min Act: -0.1700
Data Index: 3392245 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3436. Min Act: -0.1692
Data Index: 7281673 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3436. Min Act: -0.1700
Data Index: 1166513 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3436. Min Act: -0.1698
Data Index: 4491848 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3124. Min Act: -0.1700
Data Index: 8285752 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3124. Min Act: -0.1700
Data Index: 7764631 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3124. Min Act: -0.1700
Data Index: 2767162 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2811. Min Act: -0.1700
Data Index: 2824551 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2811. Min Act: -0.1700
Data Index: 4832307 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2811. Min Act: -0.1700
Data Index: 3057878 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2811. Min Act: -0.1700
Data Index: 2550708 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2811. Min Act: -0.1700
Data Index: 1076953 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.2811. Min Act: -0.1700
Data Index: 3506221 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4374. Min Range: -4.4374
Max Act: 4.3124. Min Act: -0.1700
Data Index: 3879004 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19