Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.5327. Min Act: -0.1700
Data Index: 3271025 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.5015. Min Act: -0.1700
Data Index: 3243358 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.5015. Min Act: -0.1700
Data Index: 1220318 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.5015. Min Act: -0.1700
Data Index: 6009820 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.5015. Min Act: -0.1700
Data Index: 6654653 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4702. Min Act: -0.1700
Data Index: 1468584 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.5015. Min Act: -0.1700
Data Index: 7215650 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4390. Min Act: -0.1700
Data Index: 915555 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4390. Min Act: -0.1700
Data Index: 7050829 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4390. Min Act: -0.1700
Data Index: 7050825 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4702. Min Act: -0.1700
Data Index: 5876530 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4077. Min Act: -0.1700
Data Index: 551783 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4077. Min Act: -0.1700
Data Index: 5093018 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4077. Min Act: -0.1700
Data Index: 2641407 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.4077. Min Act: -0.1700
Data Index: 8404106 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.3765. Min Act: -0.1700
Data Index: 481629 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.3765. Min Act: -0.1700
Data Index: 3337258 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.3765. Min Act: -0.1700
Data Index: 7665424 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.3765. Min Act: -0.1700
Data Index: 8694603 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5327. Min Range: -5.5327
Max Act: 5.3452. Min Act: -0.1700
Data Index: 6560950 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19