Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.6177. Min Act: -0.1700
Data Index: 5379709 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.4927. Min Act: -0.1700
Data Index: 3540919 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.4614. Min Act: -0.1700
Data Index: 7285127 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.2739. Min Act: -0.1700
Data Index: 6065139 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.2427. Min Act: -0.1700
Data Index: 5644662 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.2427. Min Act: -0.1700
Data Index: 802699 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.1802. Min Act: -0.1700
Data Index: 7905786 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.1802. Min Act: -0.1700
Data Index: 5649158 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.1489. Min Act: -0.1700
Data Index: 2405154 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.1489. Min Act: -0.1700
Data Index: 2624373 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.1177. Min Act: -0.1700
Data Index: 5425100 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.0552. Min Act: -0.1700
Data Index: 3359927 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.0239. Min Act: -0.1700
Data Index: 233666 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6177. Min Range: -6.6177
Max Act: 6.0239. Min Act: -0.1700
Data Index: 5267530 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6177. Min Range: -6.6177
Max Act: 5.9927. Min Act: -0.1700
Data Index: 6182475 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6177. Min Range: -6.6177
Max Act: 5.9927. Min Act: -0.1700
Data Index: 5955341 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6177. Min Range: -6.6177
Max Act: 5.9302. Min Act: -0.1700
Data Index: 6067584 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6177. Min Range: -6.6177
Max Act: 5.9302. Min Act: -0.1700
Data Index: 1450248 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6177. Min Range: -6.6177
Max Act: 5.9302. Min Act: -0.1700
Data Index: 6211567 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6177. Min Range: -6.6177
Max Act: 5.9614. Min Act: -0.1700
Data Index: 3259941 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19