Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4511 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2566. Min Range: -5.2566
Max Act: 5.2566. Min Act: -0.1700
Data Index: 2908153 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2566. Min Range: -5.2566
Max Act: 5.1629. Min Act: -0.1700
Data Index: 6668412 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2566. Min Range: -5.2566
Max Act: 5.1004. Min Act: -0.1699
Data Index: 5551824 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.9129. Min Act: -0.1700
Data Index: 1076216 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.8816. Min Act: -0.1688
Data Index: 3993163 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.8816. Min Act: -0.1700
Data Index: 7177021 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.8191. Min Act: -0.1697
Data Index: 5461074 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.7254. Min Act: -0.1700
Data Index: 5837097 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.6629. Min Act: -0.1699
Data Index: 1199240 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.6004. Min Act: -0.1699
Data Index: 3686349 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.5379. Min Act: -0.1700
Data Index: 6515242 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.5066. Min Act: -0.1700
Data Index: 6931581 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.5379. Min Act: -0.1700
Data Index: 4248972 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.5379. Min Act: -0.1700
Data Index: 1589827 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.5066. Min Act: -0.1700
Data Index: 749494 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.5066. Min Act: -0.1700
Data Index: 1242518 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.5066. Min Act: -0.1694
Data Index: 7183627 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.5066. Min Act: -0.1700
Data Index: 212480 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.4754. Min Act: -0.1700
Data Index: 4770784 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2566. Min Range: -5.2566
Max Act: 4.4754. Min Act: -0.1700
Data Index: 4970610 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19