Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.8586. Min Act: -0.1700
Data Index: 5116534 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.7961. Min Act: -0.1700
Data Index: 2639355 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.6711. Min Act: -0.1700
Data Index: 1332997 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.4211. Min Act: -0.1700
Data Index: 4238018 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.3586. Min Act: -0.1700
Data Index: 927045 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.3586. Min Act: -0.1700
Data Index: 2357021 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.2961. Min Act: -0.1700
Data Index: 1895570 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.2336. Min Act: -0.1700
Data Index: 414088 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.2961. Min Act: -0.1700
Data Index: 7621146 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.2336. Min Act: -0.1700
Data Index: 5857708 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1711. Min Act: -0.1700
Data Index: 4709546 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1711. Min Act: -0.1700
Data Index: 6202001 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1711. Min Act: -0.1700
Data Index: 7700759 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1711. Min Act: -0.1700
Data Index: 1288259 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1086. Min Act: -0.1700
Data Index: 5840999 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1086. Min Act: -0.1700
Data Index: 586599 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1086. Min Act: -0.1700
Data Index: 4075 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1086. Min Act: -0.1700
Data Index: 2264518 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.1086. Min Act: -0.1700
Data Index: 1387485 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8586. Min Range: -8.8586
Max Act: 8.0461. Min Act: -0.1700
Data Index: 2863223 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19