Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5305. Min Range: -10.5305
Max Act: 10.5305. Min Act: -0.1700
Data Index: 1196753 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.9055. Min Act: -0.1700
Data Index: 3215161 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.7180. Min Act: -0.1700
Data Index: 1305621 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.6555. Min Act: -0.1700
Data Index: 2121917 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.5930. Min Act: -0.1700
Data Index: 235088 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.5930. Min Act: -0.1700
Data Index: 5846322 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.5305. Min Act: -0.1700
Data Index: 4201920 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.5305. Min Act: -0.1700
Data Index: 688825 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.5305. Min Act: -0.1700
Data Index: 2706098 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.4680. Min Act: -0.1700
Data Index: 122078 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.4055. Min Act: -0.1700
Data Index: 5141737 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.3430. Min Act: -0.1700
Data Index: 2989248 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.2805. Min Act: -0.1700
Data Index: 6968927 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.2805. Min Act: -0.1700
Data Index: 4969300 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.2180. Min Act: -0.1700
Data Index: 293557 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.1555. Min Act: -0.1700
Data Index: 575500 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.1555. Min Act: -0.1700
Data Index: 1528640 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.1555. Min Act: -0.1700
Data Index: 3750680 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.0930. Min Act: -0.1700
Data Index: 4471111 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5305. Min Range: -10.5305
Max Act: 9.0930. Min Act: -0.1700
Data Index: 2437532 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19