Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5733 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.7730. Min Act: -0.1700
Data Index: 7398721 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.7418. Min Act: -0.1700
Data Index: 3249122 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.7418. Min Act: -0.1700
Data Index: 4777427 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.7418. Min Act: -0.1700
Data Index: 901649 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.7105. Min Act: -0.1700
Data Index: 6436604 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6793. Min Act: -0.1700
Data Index: 732847 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6793. Min Act: -0.1700
Data Index: 1962194 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.7105. Min Act: -0.1700
Data Index: 6245720 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6793. Min Act: -0.1700
Data Index: 2702946 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6793. Min Act: -0.1700
Data Index: 2704201 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6480. Min Act: -0.1700
Data Index: 924984 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6793. Min Act: -0.1700
Data Index: 7390806 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6168. Min Act: -0.1700
Data Index: 1093183 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.5855. Min Act: -0.1700
Data Index: 1046033 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6168. Min Act: -0.1700
Data Index: 3021625 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6168. Min Act: -0.1700
Data Index: 2888529 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6168. Min Act: -0.1700
Data Index: 5482059 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6168. Min Act: -0.1700
Data Index: 636964 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.6168. Min Act: -0.1700
Data Index: 4777423 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7730. Min Range: -7.7730
Max Act: 7.5855. Min Act: -0.1700
Data Index: 6011931 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19