Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 258 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.8253. Min Act: -0.1700
Data Index: 5017157 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.7628. Min Act: -0.1700
Data Index: 1313003 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.5128. Min Act: -0.1700
Data Index: 7133474 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.4503. Min Act: -0.1700
Data Index: 2547323 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.3878. Min Act: -0.1700
Data Index: 7196445 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.3878. Min Act: -0.1700
Data Index: 816153 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.3253. Min Act: -0.1700
Data Index: 7361729 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.2003. Min Act: -0.1700
Data Index: 2392193 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.2003. Min Act: -0.1700
Data Index: 2489599 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.1378. Min Act: -0.1700
Data Index: 3277868 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.0128. Min Act: -0.1700
Data Index: 8782780 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.0128. Min Act: -0.1700
Data Index: 1827863 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8253. Min Range: -9.8253
Max Act: 9.0128. Min Act: -0.1700
Data Index: 1186959 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8253. Min Range: -9.8253
Max Act: 8.9503. Min Act: -0.1700
Data Index: 2886191 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8253. Min Range: -9.8253
Max Act: 8.9503. Min Act: -0.1700
Data Index: 8770871 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8253. Min Range: -9.8253
Max Act: 8.9503. Min Act: -0.1700
Data Index: 2673222 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8253. Min Range: -9.8253
Max Act: 8.9503. Min Act: -0.1700
Data Index: 3989554 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8253. Min Range: -9.8253
Max Act: 8.8878. Min Act: -0.1700
Data Index: 636960 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8253. Min Range: -9.8253
Max Act: 8.9503. Min Act: -0.1700
Data Index: 4462431 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8253. Min Range: -9.8253
Max Act: 8.8253. Min Act: -0.1700
Data Index: 8436600 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19