Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5567 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.3572. Min Act: -0.1700
Data Index: 3315212 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.3101. Min Act: -0.1700
Data Index: 5044008 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 7412359 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 3221490 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 3872559 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 5120368 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 2473553 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 1553073 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 5884950 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2316. Min Act: -0.1700
Data Index: 46909 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 5357951 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2316. Min Act: -0.1700
Data Index: 7583925 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2316. Min Act: -0.1700
Data Index: 256096 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2473. Min Act: -0.1700
Data Index: 5699323 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2159. Min Act: -0.1700
Data Index: 5139823 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2159. Min Act: -0.1700
Data Index: 8021457 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2002. Min Act: -0.1700
Data Index: 2516438 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2159. Min Act: -0.1700
Data Index: 8479147 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2316. Min Act: -0.1700
Data Index: 4382828 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3572. Min Range: -3.3572
Max Act: 3.2159. Min Act: -0.1700
Data Index: 5359064 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19