Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5734 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0336. Min Range: -4.0336
Max Act: 4.0336. Min Act: -0.1700
Data Index: 5946846 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0336. Min Range: -4.0336
Max Act: 4.0023. Min Act: -0.1700
Data Index: 1600279 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9711. Min Act: -0.1700
Data Index: 2328383 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9711. Min Act: -0.1700
Data Index: 3299965 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9711. Min Act: -0.1700
Data Index: 7233167 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9711. Min Act: -0.1700
Data Index: 3457440 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 762023 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 3251610 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 8513474 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 3014112 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 8296650 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9086. Min Act: -0.1700
Data Index: 3997858 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9711. Min Act: -0.1700
Data Index: 7469011 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 1731557 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 7449217 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 72446 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 7075263 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 6369500 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9398. Min Act: -0.1700
Data Index: 5472725 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0336. Min Range: -4.0336
Max Act: 3.9086. Min Act: -0.1700
Data Index: 2340529 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19