Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5850 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.9011. Min Act: -0.1700
Data Index: 2396407 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.6199. Min Act: -0.1700
Data Index: 8044339 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.4636. Min Act: -0.1700
Data Index: 7567537 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.4636. Min Act: -0.1700
Data Index: 2485336 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.4011. Min Act: -0.1700
Data Index: 2088997 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.4011. Min Act: -0.1700
Data Index: 3856791 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3386. Min Act: -0.1700
Data Index: 3089127 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3386. Min Act: -0.1700
Data Index: 6496019 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3386. Min Act: -0.1700
Data Index: 4782072 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3699. Min Act: -0.1700
Data Index: 7655494 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3386. Min Act: -0.1700
Data Index: 7120162 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3386. Min Act: -0.1700
Data Index: 6990901 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3074. Min Act: -0.1700
Data Index: 4526525 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3074. Min Act: -0.1700
Data Index: 2253242 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3074. Min Act: -0.1700
Data Index: 2259531 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3074. Min Act: -0.1700
Data Index: 8558471 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3074. Min Act: -0.1700
Data Index: 5507644 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.3074. Min Act: -0.1700
Data Index: 1615417 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.2761. Min Act: -0.1700
Data Index: 6822835 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9011. Min Range: -4.9011
Max Act: 4.2761. Min Act: -0.1700
Data Index: 5852992 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19