Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1389 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0742. Min Range: -5.0742
Max Act: 5.0742. Min Act: -0.1700
Data Index: 3245992 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.8867. Min Act: -0.1700
Data Index: 5733748 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.8554. Min Act: -0.1700
Data Index: 2446135 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.7617. Min Act: -0.1700
Data Index: 3931240 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.7304. Min Act: -0.1700
Data Index: 6410538 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6367. Min Act: -0.1700
Data Index: 6879710 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6054. Min Act: -0.1700
Data Index: 8706187 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6054. Min Act: -0.1700
Data Index: 3208369 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6367. Min Act: -0.1700
Data Index: 7620287 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6367. Min Act: -0.1700
Data Index: 2165235 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5742. Min Act: -0.1700
Data Index: 4598547 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5742. Min Act: -0.1700
Data Index: 7408524 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6054. Min Act: -0.1700
Data Index: 7875976 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5742. Min Act: -0.1700
Data Index: 8202145 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5742. Min Act: -0.1700
Data Index: 3102831 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5117. Min Act: -0.1700
Data Index: 4672290 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5429. Min Act: -0.1700
Data Index: 2311557 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5429. Min Act: -0.1700
Data Index: 3375603 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5429. Min Act: -0.1700
Data Index: 3022176 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.5429. Min Act: -0.1700
Data Index: 7153076 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19