Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5821 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.7327. Min Act: -0.1700
Data Index: 6600486 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.6077. Min Act: -0.1700
Data Index: 3749353 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.6077. Min Act: -0.1700
Data Index: 7327131 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.5139. Min Act: -0.1700
Data Index: 7384737 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4827. Min Act: -0.1700
Data Index: 291746 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4827. Min Act: -0.1700
Data Index: 678890 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4514. Min Act: -0.1700
Data Index: 2426054 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4514. Min Act: -0.1700
Data Index: 7999991 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4514. Min Act: -0.1700
Data Index: 169888 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4202. Min Act: -0.1700
Data Index: 887023 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4514. Min Act: -0.1700
Data Index: 8516839 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4202. Min Act: -0.1700
Data Index: 7479372 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4202. Min Act: -0.1700
Data Index: 2814127 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.3889. Min Act: -0.1700
Data Index: 3124490 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.3889. Min Act: -0.1700
Data Index: 1727504 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.3889. Min Act: -0.1700
Data Index: 4584683 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.4202. Min Act: -0.1700
Data Index: 7390131 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.3889. Min Act: -0.1700
Data Index: 2404534 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.3889. Min Act: -0.1700
Data Index: 2519063 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7327. Min Range: -5.7327
Max Act: 5.3577. Min Act: -0.1700
Data Index: 2000313 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19