Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2934. Min Range: -6.2934
Max Act: 6.2934. Min Act: -0.1700
Data Index: 8126194 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2934. Min Range: -6.2934
Max Act: 6.0746. Min Act: -0.1700
Data Index: 8553918 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.9809. Min Act: -0.1700
Data Index: 3933306 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.8871. Min Act: -0.1700
Data Index: 8420498 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.9184. Min Act: -0.1700
Data Index: 4095828 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.8871. Min Act: -0.1700
Data Index: 1721818 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.8559. Min Act: -0.1700
Data Index: 4708443 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.8559. Min Act: -0.1700
Data Index: 5241210 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.8559. Min Act: -0.1700
Data Index: 8767095 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.8246. Min Act: -0.1700
Data Index: 7730288 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.8246. Min Act: -0.1700
Data Index: 4970117 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.8246. Min Act: -0.1700
Data Index: 2841637 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.7934. Min Act: -0.1700
Data Index: 2445290 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.7934. Min Act: -0.1700
Data Index: 6051341 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.7934. Min Act: -0.1700
Data Index: 1732001 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.7934. Min Act: -0.1700
Data Index: 4224166 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.7621. Min Act: -0.1700
Data Index: 6936684 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.7621. Min Act: -0.1700
Data Index: 696041 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.7621. Min Act: -0.1700
Data Index: 8706688 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2934. Min Range: -6.2934
Max Act: 5.7309. Min Act: -0.1700
Data Index: 7125598 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19