Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2389 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.8216. Min Act: -0.1700
Data Index: 7831685 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.8216. Min Act: -0.1700
Data Index: 8432465 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.7903. Min Act: -0.1700
Data Index: 8093634 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.7903. Min Act: -0.1700
Data Index: 4327648 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.7591. Min Act: -0.1700
Data Index: 1898351 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6653. Min Act: -0.1700
Data Index: 728294 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6966. Min Act: -0.1700
Data Index: 25197 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6966. Min Act: -0.1700
Data Index: 2265025 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6653. Min Act: -0.1700
Data Index: 3859293 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6653. Min Act: -0.1700
Data Index: 5516563 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6966. Min Act: -0.1700
Data Index: 7329635 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6653. Min Act: -0.1700
Data Index: 8232230 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6653. Min Act: -0.1700
Data Index: 1363424 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6341. Min Act: -0.1700
Data Index: 5317029 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.5716. Min Act: -0.1700
Data Index: 7299902 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.6028. Min Act: -0.1700
Data Index: 4428597 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.5716. Min Act: -0.1700
Data Index: 647400 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.5716. Min Act: -0.1700
Data Index: 5527508 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.5403. Min Act: -0.1700
Data Index: 8670221 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8216. Min Range: -5.8216
Max Act: 5.5403. Min Act: -0.1700
Data Index: 5285471 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19