Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.3199. Min Act: -0.1700
Data Index: 5299160 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.2574. Min Act: -0.1700
Data Index: 6646761 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.2887. Min Act: -0.1700
Data Index: 6868922 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.2574. Min Act: -0.1700
Data Index: 2670095 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.2574. Min Act: -0.1700
Data Index: 6407857 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 4915406 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.2262. Min Act: -0.1700
Data Index: 6618945 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 8015572 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 1283348 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 7077383 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.2262. Min Act: -0.1700
Data Index: 1121217 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 5027798 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 6614054 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 1862084 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 965133 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1324. Min Act: -0.1700
Data Index: 6868923 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1324. Min Act: -0.1700
Data Index: 3235147 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1324. Min Act: -0.1700
Data Index: 8574926 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1324. Min Act: -0.1700
Data Index: 6022224 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3199. Min Range: -5.3199
Max Act: 5.1324. Min Act: -0.1700
Data Index: 2304941 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19