Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4023 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1275. Min Range: -7.1275
Max Act: 7.1275. Min Act: -0.1700
Data Index: 1113227 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.9712. Min Act: -0.1700
Data Index: 1391183 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.9400. Min Act: -0.1700
Data Index: 5897405 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.8775. Min Act: -0.1700
Data Index: 7204932 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.8462. Min Act: -0.1700
Data Index: 379606 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.8150. Min Act: -0.1700
Data Index: 5220328 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.7837. Min Act: -0.1700
Data Index: 5151124 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.6900. Min Act: -0.1700
Data Index: 7268831 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.5962. Min Act: -0.1700
Data Index: 5279056 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.6275. Min Act: -0.1700
Data Index: 5788130 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.5650. Min Act: -0.1700
Data Index: 542883 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.5650. Min Act: -0.1700
Data Index: 1370257 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.5650. Min Act: -0.1700
Data Index: 7099585 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.5025. Min Act: -0.1700
Data Index: 4248272 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.4400. Min Act: -0.1700
Data Index: 1071714 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.4712. Min Act: -0.1700
Data Index: 8179755 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.4400. Min Act: -0.1700
Data Index: 4092845 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.4400. Min Act: -0.1700
Data Index: 6423681 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.4087. Min Act: -0.1700
Data Index: 3782765 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1275. Min Range: -7.1275
Max Act: 6.4400. Min Act: -0.1700
Data Index: 3056609 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19