Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4321 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.6535. Min Act: -0.1700
Data Index: 7962519 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.6222. Min Act: -0.1700
Data Index: 1529155 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.5910. Min Act: -0.1700
Data Index: 7684427 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.6222. Min Act: -0.1700
Data Index: 1850500 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.5285. Min Act: -0.1700
Data Index: 7448178 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.4660. Min Act: -0.1700
Data Index: 8157880 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.4972. Min Act: -0.1700
Data Index: 486576 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.4347. Min Act: -0.1700
Data Index: 8389804 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.4347. Min Act: -0.1700
Data Index: 7889914 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.4347. Min Act: -0.1700
Data Index: 7737778 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.4347. Min Act: -0.1700
Data Index: 5598151 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.3410. Min Act: -0.1700
Data Index: 5299915 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.3410. Min Act: -0.1700
Data Index: 8271340 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.3410. Min Act: -0.1700
Data Index: 5061002 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.3410. Min Act: -0.1700
Data Index: 251819 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.3097. Min Act: -0.1700
Data Index: 1137512 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.3097. Min Act: -0.1700
Data Index: 1493728 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.3097. Min Act: -0.1700
Data Index: 1281503 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.3097. Min Act: -0.1700
Data Index: 5075545 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6535. Min Range: -4.6535
Max Act: 4.2785. Min Act: -0.1700
Data Index: 2470185 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19