Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.6163. Min Act: -0.1700
Data Index: 3960291 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.6163. Min Act: -0.1700
Data Index: 3931833 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.5851. Min Act: -0.1700
Data Index: 2298541 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.5226. Min Act: -0.1700
Data Index: 2475500 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.4913. Min Act: -0.1700
Data Index: 1251642 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.4913. Min Act: -0.1700
Data Index: 5302931 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.4913. Min Act: -0.1700
Data Index: 5718700 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.4601. Min Act: -0.1700
Data Index: 303377 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.4913. Min Act: -0.1700
Data Index: 624809 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3976. Min Act: -0.1700
Data Index: 7827638 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3976. Min Act: -0.1700
Data Index: 6615623 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3976. Min Act: -0.1700
Data Index: 3958700 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3976. Min Act: -0.1700
Data Index: 5411052 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3976. Min Act: -0.1700
Data Index: 5270654 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3976. Min Act: -0.1700
Data Index: 3889114 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3663. Min Act: -0.1700
Data Index: 2495125 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3663. Min Act: -0.1700
Data Index: 8205842 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3663. Min Act: -0.1700
Data Index: 434602 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3976. Min Act: -0.1700
Data Index: 4032471 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6163. Min Range: -5.6163
Max Act: 5.3663. Min Act: -0.1700
Data Index: 4133309 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19