Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.7765. Min Act: -0.1700
Data Index: 999828 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.5578. Min Act: -0.1700
Data Index: 4996935 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.4953. Min Act: -0.1700
Data Index: 8445107 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.4015. Min Act: -0.1700
Data Index: 2994092 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.4015. Min Act: -0.1700
Data Index: 2648751 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.3703. Min Act: -0.1700
Data Index: 4397911 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.3703. Min Act: -0.1700
Data Index: 6704056 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.3390. Min Act: -0.1700
Data Index: 340988 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.3078. Min Act: -0.1700
Data Index: 5114018 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2765. Min Act: -0.1700
Data Index: 7581052 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2765. Min Act: -0.1700
Data Index: 6855185 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2765. Min Act: -0.1700
Data Index: 670651 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2453. Min Act: -0.1700
Data Index: 5153197 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2453. Min Act: -0.1700
Data Index: 3011452 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2140. Min Act: -0.1700
Data Index: 561897 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2453. Min Act: -0.1700
Data Index: 8279364 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2140. Min Act: -0.1700
Data Index: 3654732 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2140. Min Act: -0.1700
Data Index: 5549832 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.2140. Min Act: -0.1700
Data Index: 7082919 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7765. Min Range: -4.7765
Max Act: 4.1828. Min Act: -0.1700
Data Index: 7385774 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19