Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4588 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.8931. Min Act: -0.1700
Data Index: 5379596 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.7681. Min Act: -0.1700
Data Index: 6651493 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.7681. Min Act: -0.1700
Data Index: 4296116 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.5806. Min Act: -0.1700
Data Index: 8613832 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.5494. Min Act: -0.1700
Data Index: 4386236 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.5494. Min Act: -0.1700
Data Index: 3397188 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.4244. Min Act: -0.1700
Data Index: 3081953 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.4244. Min Act: -0.1700
Data Index: 424247 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.3619. Min Act: -0.1700
Data Index: 4267084 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.3306. Min Act: -0.1700
Data Index: 320795 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.2681. Min Act: -0.1700
Data Index: 5817811 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.2369. Min Act: -0.1700
Data Index: 5733103 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.1744. Min Act: -0.1700
Data Index: 1681401 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.2369. Min Act: -0.1700
Data Index: 3488943 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.2056. Min Act: -0.1700
Data Index: 6474213 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.2056. Min Act: -0.1700
Data Index: 6675738 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.2369. Min Act: -0.1700
Data Index: 2729398 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.1744. Min Act: -0.1700
Data Index: 5264101 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.1744. Min Act: -0.1700
Data Index: 8465094 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8931. Min Range: -7.8931
Max Act: 7.1744. Min Act: -0.1700
Data Index: 20047 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19