Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2214 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.9574. Min Act: -0.1700
Data Index: 4706055 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.9261. Min Act: -0.1700
Data Index: 4197733 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.8636. Min Act: -0.1700
Data Index: 3554157 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.8636. Min Act: -0.1700
Data Index: 4917753 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.8324. Min Act: -0.1700
Data Index: 4484801 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7566962 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.7699. Min Act: -0.1700
Data Index: 7617958 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.7699. Min Act: -0.1700
Data Index: 3340831 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.8011. Min Act: -0.1700
Data Index: 8118940 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.7074. Min Act: -0.1700
Data Index: 2277433 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.7074. Min Act: -0.1700
Data Index: 2868537 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.7074. Min Act: -0.1700
Data Index: 57008 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.6761. Min Act: -0.1700
Data Index: 4693476 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.6761. Min Act: -0.1700
Data Index: 7701243 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.6761. Min Act: -0.1700
Data Index: 3039463 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.6761. Min Act: -0.1700
Data Index: 5778410 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.6136. Min Act: -0.1700
Data Index: 2589060 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.6449. Min Act: -0.1700
Data Index: 7753931 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.6761. Min Act: -0.1700
Data Index: 3731613 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9574. Min Range: -5.9574
Max Act: 5.6136. Min Act: -0.1700
Data Index: 1556560 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19