Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4425 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.9241. Min Act: -0.1700
Data Index: 801661 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.9241. Min Act: -0.1700
Data Index: 3081338 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.9083. Min Act: -0.1700
Data Index: 2487268 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.8607. Min Act: -0.1700
Data Index: 5297159 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.8765. Min Act: -0.1700
Data Index: 8697545 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.8289. Min Act: -0.1700
Data Index: 1030624 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.8448. Min Act: -0.1700
Data Index: 4669194 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.8289. Min Act: -0.1700
Data Index: 4859452 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.8130. Min Act: -0.1700
Data Index: 5288969 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7970. Min Act: -0.1700
Data Index: 3589752 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7811. Min Act: -0.1700
Data Index: 4324937 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7811. Min Act: -0.1700
Data Index: 628246 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7811. Min Act: -0.1700
Data Index: 8165127 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7970. Min Act: -0.1700
Data Index: 3261821 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7652. Min Act: -0.1700
Data Index: 601225 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7492. Min Act: -0.1700
Data Index: 1171427 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7492. Min Act: -0.1700
Data Index: 6690707 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7652. Min Act: -0.1700
Data Index: 8655430 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7492. Min Act: -0.1700
Data Index: 2789628 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9241. Min Range: -2.9241
Max Act: 2.7492. Min Act: -0.1700
Data Index: 6875177 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19