Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4855. Min Range: -7.4855
Max Act: 7.4855. Min Act: -0.1700
Data Index: 2390561 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4855. Min Range: -7.4855
Max Act: 7.2980. Min Act: -0.1700
Data Index: 4875223 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4855. Min Range: -7.4855
Max Act: 7.2355. Min Act: -0.1700
Data Index: 5661033 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4855. Min Range: -7.4855
Max Act: 7.1105. Min Act: -0.1700
Data Index: 7051044 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4855. Min Range: -7.4855
Max Act: 7.0793. Min Act: -0.1700
Data Index: 3083846 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.9855. Min Act: -0.1700
Data Index: 1087324 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.9855. Min Act: -0.1700
Data Index: 1670735 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.9230. Min Act: -0.1700
Data Index: 1108260 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.8918. Min Act: -0.1700
Data Index: 7567281 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.9230. Min Act: -0.1700
Data Index: 8037300 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.8605. Min Act: -0.1700
Data Index: 5133864 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.8293. Min Act: -0.1700
Data Index: 7694301 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.7980. Min Act: -0.1700
Data Index: 3806337 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.7980. Min Act: -0.1700
Data Index: 2171511 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.7668. Min Act: -0.1700
Data Index: 3702868 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.7355. Min Act: -0.1700
Data Index: 468949 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.7043. Min Act: -0.1700
Data Index: 6480496 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.7043. Min Act: -0.1700
Data Index: 4665125 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.7043. Min Act: -0.1700
Data Index: 2459274 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4855. Min Range: -7.4855
Max Act: 6.7043. Min Act: -0.1700
Data Index: 3872873 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19