Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 693 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.4177. Min Act: -0.1700
Data Index: 4645230 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.4490. Min Act: -0.1700
Data Index: 2464123 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.2615. Min Act: -0.1700
Data Index: 1455590 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.9802. Min Act: -0.1700
Data Index: 7152271 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.6365. Min Act: -0.1700
Data Index: 8434365 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.8240. Min Act: -0.1700
Data Index: 7553256 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.6990. Min Act: -0.1700
Data Index: 3894638 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.6052. Min Act: -0.1700
Data Index: 7801945 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.7302. Min Act: -0.1700
Data Index: 7295795 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.7615. Min Act: -0.1700
Data Index: 700259 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.5427. Min Act: -0.1700
Data Index: 3356066 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.5740. Min Act: -0.1700
Data Index: 488814 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.4802. Min Act: -0.1700
Data Index: 1270316 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.5427. Min Act: -0.1700
Data Index: 6202412 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.3865. Min Act: -0.1700
Data Index: 7669022 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.5740. Min Act: -0.1700
Data Index: 5806948 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.4802. Min Act: -0.1700
Data Index: 7514384 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.4490. Min Act: -0.1700
Data Index: 6696439 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.5427. Min Act: -0.1700
Data Index: 2933290 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.0740. Min Act: -0.1700
Data Index: 1192579 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19