Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2091 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.9878. Min Act: -0.1700
Data Index: 7306436 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0190. Min Range: -7.0190
Max Act: 7.0190. Min Act: -0.1700
Data Index: 7408074 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0190. Min Range: -7.0190
Max Act: 7.0190. Min Act: -0.1700
Data Index: 4350354 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.9878. Min Act: -0.1700
Data Index: 7586611 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8940. Min Act: -0.1700
Data Index: 6827517 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8628. Min Act: -0.1700
Data Index: 8188247 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8628. Min Act: -0.1700
Data Index: 5140368 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8315. Min Act: -0.1700
Data Index: 6179667 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8315. Min Act: -0.1700
Data Index: 5050621 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8315. Min Act: -0.1700
Data Index: 6034169 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8315. Min Act: -0.1700
Data Index: 7882992 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8315. Min Act: -0.1700
Data Index: 3161262 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8315. Min Act: -0.1700
Data Index: 5614740 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8003. Min Act: -0.1700
Data Index: 1228171 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8003. Min Act: -0.1700
Data Index: 4092461 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8003. Min Act: -0.1700
Data Index: 4387309 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.8003. Min Act: -0.1700
Data Index: 262597 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.7690. Min Act: -0.1700
Data Index: 2287440 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.7690. Min Act: -0.1700
Data Index: 2558002 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0190. Min Range: -7.0190
Max Act: 6.7378. Min Act: -0.1700
Data Index: 2413825 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19