Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2179 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.8915. Min Act: -0.1700
Data Index: 8331500 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.6415. Min Act: -0.1700
Data Index: 4702204 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.5477. Min Act: -0.1700
Data Index: 8162457 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.3290. Min Act: -0.1700
Data Index: 7122357 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.1727. Min Act: -0.1700
Data Index: 4547368 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.2040. Min Act: -0.1700
Data Index: 4089769 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.1415. Min Act: -0.1700
Data Index: 5806904 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.1415. Min Act: -0.1700
Data Index: 507046 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.1102. Min Act: -0.1700
Data Index: 1533395 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.0790. Min Act: -0.1700
Data Index: 505348 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8915. Min Range: -7.8915
Max Act: 7.0477. Min Act: -0.1700
Data Index: 4371026 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.9852. Min Act: -0.1700
Data Index: 2599545 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.9852. Min Act: -0.1700
Data Index: 537331 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.9852. Min Act: -0.1700
Data Index: 1755685 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.9540. Min Act: -0.1700
Data Index: 4602402 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.9227. Min Act: -0.1700
Data Index: 8593695 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.9227. Min Act: -0.1700
Data Index: 7596112 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.8915. Min Act: -0.1700
Data Index: 3272180 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.8915. Min Act: -0.1700
Data Index: 8111609 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8915. Min Range: -7.8915
Max Act: 6.8915. Min Act: -0.1700
Data Index: 8180308 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19