Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6349 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0272. Min Range: -10.0272
Max Act: 10.0272. Min Act: -0.1700
Data Index: 1723418 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.7147. Min Act: -0.1700
Data Index: 7190247 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.5897. Min Act: -0.1700
Data Index: 2462078 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.4647. Min Act: -0.1700
Data Index: 6707053 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.4022. Min Act: -0.1700
Data Index: 7323273 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.4647. Min Act: -0.1700
Data Index: 577621 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.4022. Min Act: -0.1700
Data Index: 1585029 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.2772. Min Act: -0.1700
Data Index: 6160777 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.2147. Min Act: -0.1700
Data Index: 1309653 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.2147. Min Act: -0.1700
Data Index: 802972 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.2147. Min Act: -0.1700
Data Index: 3881689 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.1522. Min Act: -0.1700
Data Index: 4902962 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.1522. Min Act: -0.1700
Data Index: 586819 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.0897. Min Act: -0.1700
Data Index: 3189786 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.2147. Min Act: -0.1700
Data Index: 2248579 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.1522. Min Act: -0.1700
Data Index: 1703094 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.1522. Min Act: -0.1700
Data Index: 2743519 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.1522. Min Act: -0.1700
Data Index: 3347054 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.1522. Min Act: -0.1700
Data Index: 6465222 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0272. Min Range: -10.0272
Max Act: 9.1522. Min Act: -0.1700
Data Index: 4766482 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19