Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1381 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.7160. Min Act: -0.1700
Data Index: 1085833 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.6847. Min Act: -0.1700
Data Index: 8177001 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.6222. Min Act: -0.1700
Data Index: 8521151 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.6222. Min Act: -0.1700
Data Index: 2384093 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4972. Min Act: -0.1700
Data Index: 3410374 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4972. Min Act: -0.1700
Data Index: 4143851 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4972. Min Act: -0.1700
Data Index: 3768090 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4347. Min Act: -0.1700
Data Index: 3207807 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4347. Min Act: -0.1700
Data Index: 8469055 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4035. Min Act: -0.1700
Data Index: 5183280 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3722. Min Act: -0.1700
Data Index: 7062801 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3722. Min Act: -0.1700
Data Index: 7196241 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3097. Min Act: -0.1700
Data Index: 3551571 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3097. Min Act: -0.1700
Data Index: 3901836 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3410. Min Act: -0.1700
Data Index: 100780 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.2785. Min Act: -0.1700
Data Index: 4056093 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.2785. Min Act: -0.1700
Data Index: 424169 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3097. Min Act: -0.1700
Data Index: 7350413 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.2785. Min Act: -0.1700
Data Index: 5374330 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.2472. Min Act: -0.1700
Data Index: 3364472 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19