Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2671 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.8470. Min Act: -0.1700
Data Index: 7254050 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.6595. Min Act: -0.1700
Data Index: 6782856 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.3783. Min Act: -0.1700
Data Index: 5224464 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.2845. Min Act: -0.1700
Data Index: 7666528 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.2533. Min Act: -0.1700
Data Index: 3129359 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.3158. Min Act: -0.1700
Data Index: 7895436 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.2533. Min Act: -0.1700
Data Index: 494207 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.2220. Min Act: -0.1700
Data Index: 5410425 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.2220. Min Act: -0.1700
Data Index: 3473650 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.1908. Min Act: -0.1700
Data Index: 1025114 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.1908. Min Act: -0.1700
Data Index: 330406 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.1595. Min Act: -0.1700
Data Index: 6926684 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.1908. Min Act: -0.1700
Data Index: 4016650 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.1595. Min Act: -0.1700
Data Index: 6955689 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.1283. Min Act: -0.1700
Data Index: 7218784 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.1283. Min Act: -0.1700
Data Index: 3887178 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.0970. Min Act: -0.1700
Data Index: 3963873 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.0970. Min Act: -0.1700
Data Index: 8310805 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.1283. Min Act: -0.1700
Data Index: 7876618 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8470. Min Range: -5.8470
Max Act: 5.0658. Min Act: -0.1700
Data Index: 4407009 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19