Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1061. Min Range: -3.1061
Max Act: 3.1061. Min Act: -0.1700
Data Index: 1286820 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1061. Min Range: -3.1061
Max Act: 3.0115. Min Act: -0.1700
Data Index: 5185725 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1061. Min Range: -3.1061
Max Act: 3.0115. Min Act: -0.1700
Data Index: 3135562 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.9957. Min Act: -0.1700
Data Index: 5440674 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.9007. Min Act: -0.1700
Data Index: 2442452 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.9007. Min Act: -0.1700
Data Index: 4208189 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8531. Min Act: -0.1700
Data Index: 449228 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8690. Min Act: -0.1700
Data Index: 2008335 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8531. Min Act: -0.1700
Data Index: 3985846 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8531. Min Act: -0.1700
Data Index: 3945824 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8531. Min Act: -0.1700
Data Index: 1449439 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8372. Min Act: -0.1700
Data Index: 5370489 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8372. Min Act: -0.1700
Data Index: 1539470 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8213. Min Act: -0.1700
Data Index: 218860 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8054. Min Act: -0.1700
Data Index: 5373323 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8054. Min Act: -0.1700
Data Index: 2704038 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8054. Min Act: -0.1700
Data Index: 6895537 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8213. Min Act: -0.1700
Data Index: 8207047 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8054. Min Act: -0.1700
Data Index: 5048258 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1061. Min Range: -3.1061
Max Act: 2.8054. Min Act: -0.1700
Data Index: 2322558 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19