Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.7263. Min Act: -0.1700
Data Index: 6143904 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.5388. Min Act: -0.1700
Data Index: 6901101 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.5388. Min Act: -0.1700
Data Index: 4910096 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.3825. Min Act: -0.1700
Data Index: 2686317 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.3513. Min Act: -0.1700
Data Index: 8524227 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.3200. Min Act: -0.1700
Data Index: 4637786 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.2888. Min Act: -0.1700
Data Index: 4620351 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.2888. Min Act: -0.1700
Data Index: 4910679 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.2888. Min Act: -0.1700
Data Index: 8411297 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.2888. Min Act: -0.1700
Data Index: 2758369 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.2888. Min Act: -0.1700
Data Index: 5462058 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.2263. Min Act: -0.1700
Data Index: 4353880 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.2263. Min Act: -0.1700
Data Index: 2216618 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.1950. Min Act: -0.1700
Data Index: 584558 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.1950. Min Act: -0.1700
Data Index: 8403498 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.1950. Min Act: -0.1700
Data Index: 6555390 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.1325. Min Act: -0.1700
Data Index: 2708889 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.1013. Min Act: -0.1700
Data Index: 2666015 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.0700. Min Act: -0.1700
Data Index: 2827481 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7263. Min Range: -6.7263
Max Act: 6.1325. Min Act: -0.1700
Data Index: 659389 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19