Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 256 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2026. Min Range: -8.2026
Max Act: 8.2026. Min Act: -0.1700
Data Index: 5145098 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.9526. Min Act: -0.1700
Data Index: 4428986 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.8276. Min Act: -0.1700
Data Index: 2888873 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.6401. Min Act: -0.1700
Data Index: 874792 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.5151. Min Act: -0.1700
Data Index: 8613943 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.4526. Min Act: -0.1700
Data Index: 6168678 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.4526. Min Act: -0.1700
Data Index: 371282 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.3276. Min Act: -0.1700
Data Index: 1995548 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.3276. Min Act: -0.1700
Data Index: 4282024 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.2651. Min Act: -0.1700
Data Index: 84098 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.2026. Min Act: -0.1700
Data Index: 6190049 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.1714. Min Act: -0.1700
Data Index: 3552410 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.1401. Min Act: -0.1700
Data Index: 5441598 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.1401. Min Act: -0.1700
Data Index: 1593612 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.0776. Min Act: -0.1700
Data Index: 6120695 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.1089. Min Act: -0.1700
Data Index: 4058676 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2026. Min Range: -8.2026
Max Act: 6.9839. Min Act: -0.1700
Data Index: 1083958 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2026. Min Range: -8.2026
Max Act: 7.0151. Min Act: -0.1700
Data Index: 8052293 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2026. Min Range: -8.2026
Max Act: 6.9839. Min Act: -0.1700
Data Index: 874789 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2026. Min Range: -8.2026
Max Act: 6.9526. Min Act: -0.1700
Data Index: 2867437 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19