Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.7184. Min Act: -0.1700
Data Index: 3350217 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.7184. Min Act: -0.1700
Data Index: 7783202 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.6872. Min Act: -0.1700
Data Index: 826979 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.6872. Min Act: -0.1700
Data Index: 1945520 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.6559. Min Act: -0.1700
Data Index: 1784035 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.6872. Min Act: -0.1700
Data Index: 749630 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.6559. Min Act: -0.1700
Data Index: 4094754 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.6247. Min Act: -0.1700
Data Index: 7820283 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5934. Min Act: -0.1700
Data Index: 2862122 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.6247. Min Act: -0.1700
Data Index: 6595980 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5934. Min Act: -0.1700
Data Index: 1441606 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5622. Min Act: -0.1700
Data Index: 8676988 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5934. Min Act: -0.1700
Data Index: 2426447 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5934. Min Act: -0.1700
Data Index: 7894493 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5622. Min Act: -0.1700
Data Index: 1446216 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5934. Min Act: -0.1700
Data Index: 3052793 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5622. Min Act: -0.1700
Data Index: 3438637 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5622. Min Act: -0.1700
Data Index: 4193627 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5622. Min Act: -0.1700
Data Index: 1656833 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.5622. Min Act: -0.1700
Data Index: 5969425 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19