Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 803 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.4571. Min Act: -0.1700
Data Index: 2411349 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.3788. Min Act: -0.1700
Data Index: 413884 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.3788. Min Act: -0.1700
Data Index: 6712341 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.3474. Min Act: -0.1700
Data Index: 4530671 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.3160. Min Act: -0.1700
Data Index: 1896338 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.3160. Min Act: -0.1700
Data Index: 3084378 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2846. Min Act: -0.1700
Data Index: 6297735 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2846. Min Act: -0.1700
Data Index: 1202346 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2532. Min Act: -0.1700
Data Index: 5291157 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2689. Min Act: -0.1700
Data Index: 7347498 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2218. Min Act: -0.1700
Data Index: 8067189 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2532. Min Act: -0.1700
Data Index: 2476248 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2532. Min Act: -0.1700
Data Index: 6773 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2532. Min Act: -0.1700
Data Index: 4310969 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2375. Min Act: -0.1700
Data Index: 3377331 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2532. Min Act: -0.1700
Data Index: 3436057 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2218. Min Act: -0.1700
Data Index: 7623102 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2532. Min Act: -0.1700
Data Index: 3778156 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2375. Min Act: -0.1700
Data Index: 7802676 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4571. Min Range: -3.4571
Max Act: 3.2218. Min Act: -0.1700
Data Index: 2796225 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19