Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.8380. Min Act: -0.1700
Data Index: 884625 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.8380. Min Act: -0.1700
Data Index: 5075277 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.7442. Min Act: -0.1700
Data Index: 4147497 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.7442. Min Act: -0.1700
Data Index: 6980495 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.6817. Min Act: -0.1700
Data Index: 5309963 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.6817. Min Act: -0.1700
Data Index: 7407667 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.7130. Min Act: -0.1700
Data Index: 3737903 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.6505. Min Act: -0.1700
Data Index: 376505 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.5880. Min Act: -0.1700
Data Index: 1586507 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.6192. Min Act: -0.1700
Data Index: 2513270 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.6192. Min Act: -0.1700
Data Index: 5331693 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.6192. Min Act: -0.1700
Data Index: 6149177 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.5567. Min Act: -0.1700
Data Index: 7769278 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.5567. Min Act: -0.1700
Data Index: 8286128 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.5567. Min Act: -0.1700
Data Index: 8216822 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.5255. Min Act: -0.1700
Data Index: 1106940 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.5255. Min Act: -0.1700
Data Index: 2594469 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.4942. Min Act: -0.1700
Data Index: 8313299 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.5255. Min Act: -0.1700
Data Index: 7961860 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8380. Min Range: -5.8380
Max Act: 5.4942. Min Act: -0.1700
Data Index: 3471238 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19