Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.7679. Min Act: -0.1700
Data Index: 4138455 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.6271. Min Act: -0.1700
Data Index: 5608454 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.5488. Min Act: -0.1700
Data Index: 2888809 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.5488. Min Act: -0.1700
Data Index: 7739198 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.5332. Min Act: -0.1700
Data Index: 3560528 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.5332. Min Act: -0.1700
Data Index: 95399 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.5175. Min Act: -0.1700
Data Index: 3877944 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.5018. Min Act: -0.1700
Data Index: 498420 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4862. Min Act: -0.1700
Data Index: 6118020 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4705. Min Act: -0.1700
Data Index: 7343314 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4705. Min Act: -0.1700
Data Index: 8255271 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4705. Min Act: -0.1700
Data Index: 226629 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4548. Min Act: -0.1700
Data Index: 1656680 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4548. Min Act: -0.1700
Data Index: 6700396 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4548. Min Act: -0.1700
Data Index: 4954217 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4235. Min Act: -0.1700
Data Index: 3397317 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4392. Min Act: -0.1700
Data Index: 6438497 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4235. Min Act: -0.1700
Data Index: 4064983 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4235. Min Act: -0.1700
Data Index: 5119433 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7679. Min Range: -3.7679
Max Act: 3.4235. Min Act: -0.1700
Data Index: 7279442 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19