Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4997 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.9824. Min Act: -0.1700
Data Index: 8154299 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8886. Min Act: -0.1700
Data Index: 8418050 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8574. Min Act: -0.1700
Data Index: 16953 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8574. Min Act: -0.1700
Data Index: 6192924 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8574. Min Act: -0.1700
Data Index: 6661605 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8574. Min Act: -0.1700
Data Index: 4698554 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8574. Min Act: -0.1700
Data Index: 7910783 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8261. Min Act: -0.1700
Data Index: 4772419 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8261. Min Act: -0.1700
Data Index: 5316762 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8574. Min Act: -0.1700
Data Index: 6006008 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8261. Min Act: -0.1700
Data Index: 5633629 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8261. Min Act: -0.1700
Data Index: 7317402 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.8261. Min Act: -0.1700
Data Index: 3402093 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7948. Min Act: -0.1700
Data Index: 4884466 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7948. Min Act: -0.1700
Data Index: 6749783 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7635. Min Act: -0.1700
Data Index: 374462 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7792. Min Act: -0.1700
Data Index: 3722004 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7635. Min Act: -0.1700
Data Index: 7241948 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7635. Min Act: -0.1700
Data Index: 893987 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9824. Min Range: -3.9824
Max Act: 3.7479. Min Act: -0.1700
Data Index: 4705470 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19