Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7129. Min Range: -11.7129
Max Act: 11.7129. Min Act: -0.1700
Data Index: 8393943 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7129. Min Range: -11.7129
Max Act: 11.0879. Min Act: -0.1700
Data Index: 3766239 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.9004. Min Act: -0.1700
Data Index: 2834649 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.7129. Min Act: -0.1700
Data Index: 8821171 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.7129. Min Act: -0.1700
Data Index: 3558444 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.7129. Min Act: -0.1700
Data Index: 6372467 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.7129. Min Act: -0.1700
Data Index: 2089322 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.6504. Min Act: -0.1700
Data Index: 8333838 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.5879. Min Act: -0.1700
Data Index: 918998 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.5879. Min Act: -0.1700
Data Index: 2788076 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.5879. Min Act: -0.1646
Data Index: 4121188 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.5254. Min Act: -0.1695
Data Index: 1904316 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.4629. Min Act: -0.1699
Data Index: 2591550 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.4629. Min Act: -0.1700
Data Index: 5460710 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.4629. Min Act: -0.1698
Data Index: 6760406 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.4004. Min Act: -0.1700
Data Index: 2446728 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.3379. Min Act: -0.1700
Data Index: 3243097 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.3379. Min Act: -0.1693
Data Index: 5019992 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.3379. Min Act: -0.1698
Data Index: 4132536 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7129. Min Range: -11.7129
Max Act: 10.2754. Min Act: -0.1700
Data Index: 919016 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19