Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4319. Min Range: -7.4319
Max Act: 7.4319. Min Act: -0.1700
Data Index: 6555072 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4319. Min Range: -7.4319
Max Act: 7.0257. Min Act: -0.1700
Data Index: 6106735 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4319. Min Range: -7.4319
Max Act: 7.0257. Min Act: -0.1700
Data Index: 2796463 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.8382. Min Act: -0.1700
Data Index: 4373476 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.8069. Min Act: -0.1700
Data Index: 6379153 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.7757. Min Act: -0.1700
Data Index: 2420840 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.7757. Min Act: -0.1700
Data Index: 6642322 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.7132. Min Act: -0.1700
Data Index: 5116289 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.6819. Min Act: -0.1700
Data Index: 2824163 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.6507. Min Act: -0.1700
Data Index: 5594574 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.6507. Min Act: -0.1700
Data Index: 1880936 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.6194. Min Act: -0.1700
Data Index: 2629688 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.6194. Min Act: -0.1700
Data Index: 7820979 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.5882. Min Act: -0.1700
Data Index: 1854546 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.5569. Min Act: -0.1700
Data Index: 876920 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.5882. Min Act: -0.1700
Data Index: 4661171 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.5569. Min Act: -0.1700
Data Index: 7949108 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.4632. Min Act: -0.1700
Data Index: 4461555 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.4632. Min Act: -0.1700
Data Index: 3129075 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4319. Min Range: -7.4319
Max Act: 6.4632. Min Act: -0.1700
Data Index: 2364392 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19