Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6383 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.6293. Min Act: -0.1700
Data Index: 1360637 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.5668. Min Act: -0.1700
Data Index: 30914 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.4105. Min Act: -0.1700
Data Index: 3828547 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.3480. Min Act: -0.1700
Data Index: 7419757 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2855. Min Act: -0.1700
Data Index: 2566807 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.3480. Min Act: -0.1700
Data Index: 5754727 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.3168. Min Act: -0.1700
Data Index: 6204508 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2855. Min Act: -0.1700
Data Index: 8167551 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2542. Min Act: -0.1700
Data Index: 8338400 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2542. Min Act: -0.1700
Data Index: 139967 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2542. Min Act: -0.1700
Data Index: 1510279 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2230. Min Act: -0.1700
Data Index: 7665639 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2230. Min Act: -0.1700
Data Index: 7097872 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2230. Min Act: -0.1700
Data Index: 4926344 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2230. Min Act: -0.1700
Data Index: 983703 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2230. Min Act: -0.1700
Data Index: 4567459 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2230. Min Act: -0.1700
Data Index: 4718626 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.1917. Min Act: -0.1700
Data Index: 2284821 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.1917. Min Act: -0.1700
Data Index: 4217850 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6293. Min Range: -4.6293
Max Act: 4.2230. Min Act: -0.1700
Data Index: 2945813 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19