Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.1596. Min Act: -0.1700
Data Index: 2868049 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.1283. Min Act: -0.1700
Data Index: 1328018 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.1283. Min Act: -0.1700
Data Index: 7873482 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0971. Min Act: -0.1700
Data Index: 6402228 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0971. Min Act: -0.1700
Data Index: 3189785 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0658. Min Act: -0.1700
Data Index: 1585710 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0346. Min Act: -0.1700
Data Index: 6867813 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0346. Min Act: -0.1700
Data Index: 6220409 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0346. Min Act: -0.1700
Data Index: 2055174 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0346. Min Act: -0.1700
Data Index: 308378 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0346. Min Act: -0.1700
Data Index: 700883 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0346. Min Act: -0.1700
Data Index: 3235667 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0658. Min Act: -0.1700
Data Index: 8151963 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0033. Min Act: -0.1700
Data Index: 3147140 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0346. Min Act: -0.1700
Data Index: 5846493 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0033. Min Act: -0.1700
Data Index: 5785710 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0033. Min Act: -0.1700
Data Index: 3864316 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0033. Min Act: -0.1700
Data Index: 989344 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0033. Min Act: -0.1700
Data Index: 3895515 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1596. Min Range: -5.1596
Max Act: 5.0033. Min Act: -0.1700
Data Index: 3496077 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19