Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.2259. Min Act: -0.1700
Data Index: 4582436 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1947. Min Act: -0.1700
Data Index: 6398669 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1634. Min Act: -0.1700
Data Index: 563606 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1634. Min Act: -0.1700
Data Index: 2846931 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1634. Min Act: -0.1700
Data Index: 5453990 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1322. Min Act: -0.1700
Data Index: 1072636 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1322. Min Act: -0.1700
Data Index: 1969120 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1322. Min Act: -0.1700
Data Index: 1021920 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1009. Min Act: -0.1700
Data Index: 4028384 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1322. Min Act: -0.1700
Data Index: 7114387 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0697. Min Act: -0.1700
Data Index: 5806548 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0697. Min Act: -0.1700
Data Index: 8830768 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0697. Min Act: -0.1700
Data Index: 4231804 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0697. Min Act: -0.1700
Data Index: 7248821 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0697. Min Act: -0.1700
Data Index: 4758754 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0072. Min Act: -0.1700
Data Index: 3427983 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0072. Min Act: -0.1700
Data Index: 251604 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 74760 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0697. Min Act: -0.1700
Data Index: 1759993 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 2785111 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19