Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2147 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1296. Min Range: -9.1296
Max Act: 9.1296. Min Act: -0.1700
Data Index: 6226171 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.8796. Min Act: -0.1700
Data Index: 3248728 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.3796. Min Act: -0.1700
Data Index: 6138081 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.3796. Min Act: -0.1700
Data Index: 106883 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.3171. Min Act: -0.1700
Data Index: 6310200 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.2546. Min Act: -0.1700
Data Index: 8580504 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.2546. Min Act: -0.1700
Data Index: 5836796 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.1921. Min Act: -0.1700
Data Index: 7469257 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.1921. Min Act: -0.1700
Data Index: 854259 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.1296. Min Act: -0.1700
Data Index: 3145513 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.1296. Min Act: -0.1700
Data Index: 5720433 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.0671. Min Act: -0.1700
Data Index: 7099007 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.1296. Min Act: -0.1700
Data Index: 6833473 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.0671. Min Act: -0.1700
Data Index: 4167813 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.0046. Min Act: -0.1700
Data Index: 4564938 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.0046. Min Act: -0.1700
Data Index: 4359892 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.0046. Min Act: -0.1700
Data Index: 3328483 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.0046. Min Act: -0.1700
Data Index: 614567 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.0046. Min Act: -0.1700
Data Index: 3391838 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1296. Min Range: -9.1296
Max Act: 8.0046. Min Act: -0.1700
Data Index: 7294115 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19