Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.6712. Min Act: -0.1700
Data Index: 7485030 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.6087. Min Act: -0.1700
Data Index: 7905578 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.4837. Min Act: -0.1700
Data Index: 3573236 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.4212. Min Act: -0.1700
Data Index: 768821 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.3587. Min Act: -0.1700
Data Index: 4019746 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.3274. Min Act: -0.1700
Data Index: 4717928 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.3274. Min Act: -0.1700
Data Index: 8790315 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.2649. Min Act: -0.1700
Data Index: 1277787 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.1712. Min Act: -0.1700
Data Index: 2099009 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.2337. Min Act: -0.1700
Data Index: 546281 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.2024. Min Act: -0.1700
Data Index: 4986712 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.1399. Min Act: -0.1700
Data Index: 1987139 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.1712. Min Act: -0.1700
Data Index: 4717930 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.1712. Min Act: -0.1700
Data Index: 610097 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.1712. Min Act: -0.1700
Data Index: 8123601 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.1399. Min Act: -0.1700
Data Index: 4827842 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.0774. Min Act: -0.1700
Data Index: 3100704 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.0774. Min Act: -0.1700
Data Index: 8628588 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.0462. Min Act: -0.1700
Data Index: 6114467 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6712. Min Range: -7.6712
Max Act: 7.1087. Min Act: -0.1700
Data Index: 3018574 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19