Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1243 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.4413. Min Act: -0.1700
Data Index: 5441594 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.3788. Min Act: -0.1700
Data Index: 7706364 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.3788. Min Act: -0.1700
Data Index: 6506889 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.3163. Min Act: -0.1700
Data Index: 460797 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.3163. Min Act: -0.1700
Data Index: 1669094 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.2538. Min Act: -0.1700
Data Index: 2239435 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.2538. Min Act: -0.1700
Data Index: 588386 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.2538. Min Act: -0.1700
Data Index: 6088379 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.1913. Min Act: -0.1700
Data Index: 4161183 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.1913. Min Act: -0.1700
Data Index: 2560240 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.1288. Min Act: -0.1700
Data Index: 7725507 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.0663. Min Act: -0.1700
Data Index: 8076224 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.1288. Min Act: -0.1700
Data Index: 2967457 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.0038. Min Act: -0.1700
Data Index: 2871909 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.0038. Min Act: -0.1700
Data Index: 5249354 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.0038. Min Act: -0.1700
Data Index: 7431514 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.0038. Min Act: -0.1700
Data Index: 5975137 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.0038. Min Act: -0.1700
Data Index: 6057738 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.0038. Min Act: -0.1700
Data Index: 201926 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4413. Min Range: -8.4413
Max Act: 8.0038. Min Act: -0.1700
Data Index: 3545489 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19