Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1348. Min Range: -5.1348
Max Act: 5.1348. Min Act: -0.1700
Data Index: 4094742 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1348. Min Range: -5.1348
Max Act: 5.1036. Min Act: -0.1700
Data Index: 683290 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1348. Min Range: -5.1348
Max Act: 5.0723. Min Act: -0.1700
Data Index: 2505996 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1348. Min Range: -5.1348
Max Act: 5.0723. Min Act: -0.1700
Data Index: 6447620 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1348. Min Range: -5.1348
Max Act: 5.0098. Min Act: -0.1700
Data Index: 6775274 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1348. Min Range: -5.1348
Max Act: 5.0098. Min Act: -0.1700
Data Index: 4254178 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1348. Min Range: -5.1348
Max Act: 5.0098. Min Act: -0.1700
Data Index: 7791199 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1348. Min Range: -5.1348
Max Act: 5.0098. Min Act: -0.1700
Data Index: 5078135 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9786. Min Act: -0.1700
Data Index: 4042800 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9786. Min Act: -0.1700
Data Index: 2394235 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9473. Min Act: -0.1700
Data Index: 3436458 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9786. Min Act: -0.1700
Data Index: 8216967 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9473. Min Act: -0.1700
Data Index: 534231 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.8848. Min Act: -0.1700
Data Index: 7611750 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9473. Min Act: -0.1700
Data Index: 6552317 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9473. Min Act: -0.1700
Data Index: 4373075 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9161. Min Act: -0.1700
Data Index: 3490166 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9161. Min Act: -0.1700
Data Index: 3372422 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.9161. Min Act: -0.1700
Data Index: 2199367 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1348. Min Range: -5.1348
Max Act: 4.8848. Min Act: -0.1700
Data Index: 4317843 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19