Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.4348. Min Act: -0.1700
Data Index: 3162389 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.4035. Min Act: -0.1700
Data Index: 5401112 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.4192. Min Act: -0.1700
Data Index: 3877771 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.3878. Min Act: -0.1700
Data Index: 3090042 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.3878. Min Act: -0.1700
Data Index: 7977133 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.4035. Min Act: -0.1700
Data Index: 2703151 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.3721. Min Act: -0.1700
Data Index: 2294930 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.3564. Min Act: -0.1700
Data Index: 8506006 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.3251. Min Act: -0.1700
Data Index: 1350640 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.3094. Min Act: -0.1700
Data Index: 1692631 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2937. Min Act: -0.1700
Data Index: 8358577 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2937. Min Act: -0.1700
Data Index: 6287108 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2937. Min Act: -0.1700
Data Index: 7507753 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2780. Min Act: -0.1700
Data Index: 6274841 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2780. Min Act: -0.1700
Data Index: 1622565 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2623. Min Act: -0.1700
Data Index: 5550959 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2465. Min Act: -0.1700
Data Index: 354234 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2465. Min Act: -0.1700
Data Index: 7477750 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2308. Min Act: -0.1700
Data Index: 5113088 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4348. Min Range: -3.4348
Max Act: 3.2151. Min Act: -0.1700
Data Index: 5789952 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19