Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 546 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.6950. Min Act: -0.1700
Data Index: 1773908 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.6950. Min Act: -0.1700
Data Index: 2218979 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.3200. Min Act: -0.1700
Data Index: 6021099 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.3200. Min Act: -0.1700
Data Index: 3824999 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.3200. Min Act: -0.1700
Data Index: 2238776 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.3200. Min Act: -0.1700
Data Index: 3443168 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.2575. Min Act: -0.1700
Data Index: 8819147 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.2575. Min Act: -0.1700
Data Index: 6134639 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.1950. Min Act: -0.1700
Data Index: 8084508 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.2575. Min Act: -0.1700
Data Index: 4680638 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.2575. Min Act: -0.1700
Data Index: 4780315 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.1950. Min Act: -0.1700
Data Index: 4785153 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.1325. Min Act: -0.1700
Data Index: 6222742 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.1325. Min Act: -0.1700
Data Index: 3402596 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.1325. Min Act: -0.1700
Data Index: 3848378 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.0700. Min Act: -0.1700
Data Index: 2407362 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.0700. Min Act: -0.1700
Data Index: 2206433 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.0700. Min Act: -0.1700
Data Index: 6109792 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.0700. Min Act: -0.1700
Data Index: 4277042 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6950. Min Range: -8.6950
Max Act: 8.0700. Min Act: -0.1700
Data Index: 1854518 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19