Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2156 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2658. Min Range: -7.2658
Max Act: 7.2658. Min Act: -0.1700
Data Index: 4803165 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2658. Min Range: -7.2658
Max Act: 7.2033. Min Act: -0.1700
Data Index: 5351073 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2658. Min Range: -7.2658
Max Act: 7.1408. Min Act: -0.1700
Data Index: 253246 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.9220. Min Act: -0.1700
Data Index: 5427337 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.8595. Min Act: -0.1700
Data Index: 1641657 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.8283. Min Act: -0.1700
Data Index: 865885 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.8283. Min Act: -0.1700
Data Index: 2279040 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7970. Min Act: -0.1700
Data Index: 5384810 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7658. Min Act: -0.1700
Data Index: 1612135 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7345. Min Act: -0.1700
Data Index: 544091 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7658. Min Act: -0.1700
Data Index: 7731041 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7345. Min Act: -0.1700
Data Index: 8800692 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7345. Min Act: -0.1700
Data Index: 173428 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7345. Min Act: -0.1700
Data Index: 1340183 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7033. Min Act: -0.1700
Data Index: 544092 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.7033. Min Act: -0.1700
Data Index: 8572451 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.6408. Min Act: -0.1700
Data Index: 2695324 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.6095. Min Act: -0.1700
Data Index: 6041228 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.5783. Min Act: -0.1700
Data Index: 2018769 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2658. Min Range: -7.2658
Max Act: 6.5470. Min Act: -0.1700
Data Index: 6353207 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19