Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 479 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.2305. Min Act: -0.1700
Data Index: 6005638 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.1055. Min Act: -0.1700
Data Index: 3751118 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0742. Min Act: -0.1700
Data Index: 7159426 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0117. Min Act: -0.1700
Data Index: 162473 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9805. Min Act: -0.1700
Data Index: 2934988 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9805. Min Act: -0.1700
Data Index: 421631 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9492. Min Act: -0.1700
Data Index: 7848188 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9492. Min Act: -0.1700
Data Index: 225828 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9492. Min Act: -0.1700
Data Index: 4425744 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9492. Min Act: -0.1700
Data Index: 5894312 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9179. Min Act: -0.1700
Data Index: 449296 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9179. Min Act: -0.1700
Data Index: 405151 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.9179. Min Act: -0.1700
Data Index: 957966 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.8867. Min Act: -0.1700
Data Index: 5438981 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.8554. Min Act: -0.1700
Data Index: 6165558 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.8867. Min Act: -0.1700
Data Index: 479077 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.8554. Min Act: -0.1700
Data Index: 8398339 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.8554. Min Act: -0.1700
Data Index: 3337740 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.8241. Min Act: -0.1700
Data Index: 3181731 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2305. Min Range: -4.2305
Max Act: 3.7929. Min Act: -0.1700
Data Index: 3281259 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19