Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.5460. Min Act: -0.1700
Data Index: 8219562 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.4210. Min Act: -0.1700
Data Index: 991557 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.3897. Min Act: -0.1700
Data Index: 2978526 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.3272. Min Act: -0.1700
Data Index: 7425022 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.3585. Min Act: -0.1700
Data Index: 3725929 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.3585. Min Act: -0.1700
Data Index: 5899841 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2647. Min Act: -0.1700
Data Index: 7040604 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2647. Min Act: -0.1700
Data Index: 8770158 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2647. Min Act: -0.1700
Data Index: 5664989 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2335. Min Act: -0.1700
Data Index: 2081185 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2335. Min Act: -0.1700
Data Index: 7868014 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2647. Min Act: -0.1700
Data Index: 1512142 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2335. Min Act: -0.1700
Data Index: 3946076 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2335. Min Act: -0.1700
Data Index: 2872905 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2022. Min Act: -0.1700
Data Index: 5390749 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2022. Min Act: -0.1700
Data Index: 7796284 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2022. Min Act: -0.1700
Data Index: 3035779 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2022. Min Act: -0.1700
Data Index: 8438781 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.2022. Min Act: -0.1700
Data Index: 3311821 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5460. Min Range: -5.5460
Max Act: 5.1710. Min Act: -0.1700
Data Index: 2873191 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19