Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.6700. Min Act: -0.1700
Data Index: 1070755 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.6075. Min Act: -0.1700
Data Index: 5920481 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.6387. Min Act: -0.1700
Data Index: 949056 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.6387. Min Act: -0.1700
Data Index: 5523412 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.5450. Min Act: -0.1700
Data Index: 3433683 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.4512. Min Act: -0.1700
Data Index: 4580308 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.4200. Min Act: -0.1700
Data Index: 8672365 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.4200. Min Act: -0.1700
Data Index: 1208683 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 5839680 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3575. Min Act: -0.1700
Data Index: 3297253 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 1536286 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3887. Min Act: -0.1700
Data Index: 2608430 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3575. Min Act: -0.1700
Data Index: 5158272 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3575. Min Act: -0.1700
Data Index: 4159743 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3262. Min Act: -0.1700
Data Index: 2172658 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3262. Min Act: -0.1700
Data Index: 3492653 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.3575. Min Act: -0.1700
Data Index: 1550543 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.2637. Min Act: -0.1700
Data Index: 6088980 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.2950. Min Act: -0.1700
Data Index: 8002923 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6700. Min Range: -4.6700
Max Act: 4.2324. Min Act: -0.1700
Data Index: 1057850 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19