Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5564 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2838. Min Range: -7.2838
Max Act: 7.2838. Min Act: -0.1700
Data Index: 1665236 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2838. Min Range: -7.2838
Max Act: 7.1275. Min Act: -0.1700
Data Index: 8228354 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.9400. Min Act: -0.1700
Data Index: 6807971 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.8463. Min Act: -0.1700
Data Index: 4302714 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.8463. Min Act: -0.1700
Data Index: 8761621 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.8150. Min Act: -0.1700
Data Index: 4876529 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.7213. Min Act: -0.1700
Data Index: 8290116 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.7213. Min Act: -0.1700
Data Index: 3118662 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.6900. Min Act: -0.1700
Data Index: 1490335 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.5650. Min Act: -0.1700
Data Index: 838745 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.5963. Min Act: -0.1700
Data Index: 698091 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.5963. Min Act: -0.1700
Data Index: 285607 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.5963. Min Act: -0.1700
Data Index: 5089483 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.5650. Min Act: -0.1700
Data Index: 7696182 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.5338. Min Act: -0.1700
Data Index: 6334573 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.5338. Min Act: -0.1700
Data Index: 5661242 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.5025. Min Act: -0.1700
Data Index: 6362171 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.4713. Min Act: -0.1700
Data Index: 6464424 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.4713. Min Act: -0.1700
Data Index: 4681023 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2838. Min Range: -7.2838
Max Act: 6.4713. Min Act: -0.1700
Data Index: 8177822 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19