Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2383. Min Range: -4.2383
Max Act: 4.2383. Min Act: -0.1700
Data Index: 609259 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2383. Min Range: -4.2383
Max Act: 4.1445. Min Act: -0.1700
Data Index: 6952055 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2383. Min Range: -4.2383
Max Act: 4.0195. Min Act: -0.1700
Data Index: 3069023 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.9570. Min Act: -0.1700
Data Index: 8590426 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8945. Min Act: -0.1700
Data Index: 2346788 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8632. Min Act: -0.1700
Data Index: 8174080 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8632. Min Act: -0.1700
Data Index: 6015234 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8319. Min Act: -0.1700
Data Index: 3750435 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8006. Min Act: -0.1700
Data Index: 8606922 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8006. Min Act: -0.1700
Data Index: 489878 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8006. Min Act: -0.1700
Data Index: 5399011 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8006. Min Act: -0.1700
Data Index: 4039284 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8006. Min Act: -0.1700
Data Index: 7872266 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8006. Min Act: -0.1700
Data Index: 3975210 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.7694. Min Act: -0.1700
Data Index: 1979403 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.7694. Min Act: -0.1700
Data Index: 625822 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.7694. Min Act: -0.1700
Data Index: 3209273 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.8006. Min Act: -0.1700
Data Index: 7140884 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.7381. Min Act: -0.1700
Data Index: 7408099 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2383. Min Range: -4.2383
Max Act: 3.7381. Min Act: -0.1700
Data Index: 4395336 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19