Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1143 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.4772. Min Act: -0.1700
Data Index: 6190248 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.4772. Min Act: -0.1700
Data Index: 3198745 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.4147. Min Act: -0.1700
Data Index: 7663325 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.3522. Min Act: -0.1700
Data Index: 606785 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.3835. Min Act: -0.1700
Data Index: 5408997 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.3522. Min Act: -0.1700
Data Index: 8750239 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.3522. Min Act: -0.1700
Data Index: 606784 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.3210. Min Act: -0.1700
Data Index: 6034694 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.3210. Min Act: -0.1700
Data Index: 3828407 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2897. Min Act: -0.1700
Data Index: 5866606 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2897. Min Act: -0.1700
Data Index: 400760 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2585. Min Act: -0.1700
Data Index: 2324953 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2585. Min Act: -0.1700
Data Index: 5536164 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2585. Min Act: -0.1700
Data Index: 772319 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2585. Min Act: -0.1700
Data Index: 3293403 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2585. Min Act: -0.1700
Data Index: 2567428 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2585. Min Act: -0.1700
Data Index: 387570 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.1960. Min Act: -0.1700
Data Index: 1400119 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2272. Min Act: -0.1700
Data Index: 6094096 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4772. Min Range: -6.4772
Max Act: 6.2272. Min Act: -0.1700
Data Index: 1339348 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19