Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.6487. Min Act: -0.1700
Data Index: 7639300 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.6174. Min Act: -0.1700
Data Index: 2679517 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.5862. Min Act: -0.1700
Data Index: 2962760 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.5549. Min Act: -0.1700
Data Index: 7876547 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.5237. Min Act: -0.1700
Data Index: 7910342 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.5237. Min Act: -0.1700
Data Index: 1681051 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.4924. Min Act: -0.1700
Data Index: 6668044 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.4612. Min Act: -0.1700
Data Index: 8049091 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.4924. Min Act: -0.1700
Data Index: 2716922 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.4612. Min Act: -0.1700
Data Index: 2979828 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.4612. Min Act: -0.1700
Data Index: 965027 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.4612. Min Act: -0.1700
Data Index: 8464880 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.3987. Min Act: -0.1700
Data Index: 3358313 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.3674. Min Act: -0.1700
Data Index: 1432041 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.3987. Min Act: -0.1700
Data Index: 2319040 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.3987. Min Act: -0.1700
Data Index: 4617514 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.3987. Min Act: -0.1700
Data Index: 562477 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.3362. Min Act: -0.1700
Data Index: 3779233 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.3362. Min Act: -0.1700
Data Index: 5530189 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6487. Min Range: -4.6487
Max Act: 4.3362. Min Act: -0.1700
Data Index: 1957766 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19