Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4387 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.9552. Min Act: -0.1700
Data Index: 1209400 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.8302. Min Act: -0.1700
Data Index: 5747515 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.7677. Min Act: -0.1700
Data Index: 5848523 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.7052. Min Act: -0.1700
Data Index: 5098974 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.4552. Min Act: -0.1700
Data Index: 717159 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.4240. Min Act: -0.1700
Data Index: 6996218 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.4240. Min Act: -0.1700
Data Index: 5532736 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.4240. Min Act: -0.1700
Data Index: 7619769 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.3927. Min Act: -0.1700
Data Index: 8681844 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.3615. Min Act: -0.1700
Data Index: 1209399 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.3302. Min Act: -0.1700
Data Index: 5412475 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2677. Min Act: -0.1700
Data Index: 6886178 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2677. Min Act: -0.1700
Data Index: 1723470 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2677. Min Act: -0.1700
Data Index: 462409 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2677. Min Act: -0.1700
Data Index: 8468727 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2677. Min Act: -0.1700
Data Index: 6209388 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2365. Min Act: -0.1700
Data Index: 6055073 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2365. Min Act: -0.1700
Data Index: 1676727 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2052. Min Act: -0.1700
Data Index: 6047371 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2052. Min Act: -0.1700
Data Index: 7722886 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19