Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 143 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.5212. Min Act: -0.1700
Data Index: 3557594 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.3962. Min Act: -0.1700
Data Index: 7151954 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.3962. Min Act: -0.1700
Data Index: 1771211 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.3962. Min Act: -0.1700
Data Index: 8155505 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.3337. Min Act: -0.1700
Data Index: 8576557 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.2712. Min Act: -0.1700
Data Index: 938078 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.2712. Min Act: -0.1700
Data Index: 4791308 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.2399. Min Act: -0.1700
Data Index: 3933402 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.2399. Min Act: -0.1700
Data Index: 2442281 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.2399. Min Act: -0.1700
Data Index: 7041876 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.1462. Min Act: -0.1700
Data Index: 5666852 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.1462. Min Act: -0.1700
Data Index: 8519150 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.1149. Min Act: -0.1700
Data Index: 3067384 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.0837. Min Act: -0.1700
Data Index: 4759511 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.0524. Min Act: -0.1700
Data Index: 3753354 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.0212. Min Act: -0.1700
Data Index: 1417893 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.0837. Min Act: -0.1700
Data Index: 7366328 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.0837. Min Act: -0.1700
Data Index: 3894860 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.0212. Min Act: -0.1700
Data Index: 2811057 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5212. Min Range: -7.5212
Max Act: 7.0524. Min Act: -0.1700
Data Index: 6966547 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19