Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0700. Min Range: -9.0700
Max Act: 9.0700. Min Act: -0.1700
Data Index: 4481312 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.9450. Min Act: -0.1700
Data Index: 991549 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.8825. Min Act: -0.1700
Data Index: 8761817 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.8200. Min Act: -0.1700
Data Index: 7864877 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.7575. Min Act: -0.1700
Data Index: 3378500 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.6950. Min Act: -0.1700
Data Index: 2482613 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.6950. Min Act: -0.1700
Data Index: 5898167 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.6950. Min Act: -0.1700
Data Index: 3444837 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.6325. Min Act: -0.1700
Data Index: 5114452 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.6325. Min Act: -0.1700
Data Index: 8770921 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.6325. Min Act: -0.1700
Data Index: 7441318 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.6325. Min Act: -0.1700
Data Index: 5141411 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.6325. Min Act: -0.1700
Data Index: 898550 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.5700. Min Act: -0.1700
Data Index: 4477652 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.5700. Min Act: -0.1700
Data Index: 707005 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.5700. Min Act: -0.1700
Data Index: 1446600 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.5075. Min Act: -0.1700
Data Index: 1049311 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.5075. Min Act: -0.1700
Data Index: 5785385 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.5075. Min Act: -0.1700
Data Index: 1237750 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0700. Min Range: -9.0700
Max Act: 8.4450. Min Act: -0.1700
Data Index: 726957 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19