Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4070 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.9399. Min Act: -0.1700
Data Index: 7813357 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.7211. Min Act: -0.1700
Data Index: 1356921 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.6586. Min Act: -0.1700
Data Index: 4473215 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.5649. Min Act: -0.1700
Data Index: 8038576 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.5336. Min Act: -0.1700
Data Index: 3612353 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.5336. Min Act: -0.1700
Data Index: 3253280 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.5336. Min Act: -0.1700
Data Index: 1180547 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.5024. Min Act: -0.1700
Data Index: 5433090 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.4711. Min Act: -0.1700
Data Index: 80376 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.4711. Min Act: -0.1700
Data Index: 6875192 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.4086. Min Act: -0.1700
Data Index: 6859044 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.4399. Min Act: -0.1700
Data Index: 8097530 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.4399. Min Act: -0.1700
Data Index: 1107770 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.3774. Min Act: -0.1700
Data Index: 2296146 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.4086. Min Act: -0.1700
Data Index: 4916083 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.4086. Min Act: -0.1700
Data Index: 5663590 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.4086. Min Act: -0.1700
Data Index: 4194616 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.3774. Min Act: -0.1700
Data Index: 1458910 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.3461. Min Act: -0.1700
Data Index: 2284594 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.3774. Min Act: -0.1700
Data Index: 5861695 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19