Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.8629. Min Act: -0.1700
Data Index: 2830411 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.4567. Min Act: -0.1700
Data Index: 8560317 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.3942. Min Act: -0.1700
Data Index: 7730017 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.3629. Min Act: -0.1700
Data Index: 2817748 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.2067. Min Act: -0.1700
Data Index: 5421193 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.2067. Min Act: -0.1700
Data Index: 4495034 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.1754. Min Act: -0.1700
Data Index: 510962 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.1754. Min Act: -0.1700
Data Index: 3417130 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.1129. Min Act: -0.1700
Data Index: 6021556 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.1129. Min Act: -0.1700
Data Index: 7398044 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.0817. Min Act: -0.1700
Data Index: 7614379 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.0192. Min Act: -0.1700
Data Index: 3152424 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.0192. Min Act: -0.1700
Data Index: 4004053 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8629. Min Range: -6.8629
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2889011 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8629. Min Range: -6.8629
Max Act: 5.9879. Min Act: -0.1700
Data Index: 5715690 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8629. Min Range: -6.8629
Max Act: 5.9879. Min Act: -0.1700
Data Index: 1097657 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8629. Min Range: -6.8629
Max Act: 5.9567. Min Act: -0.1700
Data Index: 3307854 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8629. Min Range: -6.8629
Max Act: 5.9567. Min Act: -0.1700
Data Index: 3605436 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8629. Min Range: -6.8629
Max Act: 5.9567. Min Act: -0.1700
Data Index: 3376774 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8629. Min Range: -6.8629
Max Act: 5.9254. Min Act: -0.1700
Data Index: 5119795 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19