Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.2120. Min Act: -0.1700
Data Index: 2602918 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.1808. Min Act: -0.1700
Data Index: 559075 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.1183. Min Act: -0.1700
Data Index: 279282 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.1183. Min Act: -0.1700
Data Index: 6959290 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0870. Min Act: -0.1700
Data Index: 8688449 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0870. Min Act: -0.1700
Data Index: 980151 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0870. Min Act: -0.1700
Data Index: 5477294 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0558. Min Act: -0.1700
Data Index: 8752212 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0558. Min Act: -0.1700
Data Index: 8792356 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0558. Min Act: -0.1700
Data Index: 3755720 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0245. Min Act: -0.1700
Data Index: 98858 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0558. Min Act: -0.1700
Data Index: 2112322 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0245. Min Act: -0.1700
Data Index: 4060647 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0245. Min Act: -0.1700
Data Index: 307730 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2120. Min Range: -5.2120
Max Act: 5.0245. Min Act: -0.1700
Data Index: 2562345 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2120. Min Range: -5.2120
Max Act: 4.9933. Min Act: -0.1700
Data Index: 3050104 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2120. Min Range: -5.2120
Max Act: 4.9933. Min Act: -0.1700
Data Index: 6647126 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2120. Min Range: -5.2120
Max Act: 4.9620. Min Act: -0.1700
Data Index: 8556229 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2120. Min Range: -5.2120
Max Act: 4.9933. Min Act: -0.1700
Data Index: 564758 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2120. Min Range: -5.2120
Max Act: 4.9933. Min Act: -0.1700
Data Index: 8581231 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19