Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.5388. Min Act: -0.1700
Data Index: 1126813 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.5388. Min Act: -0.1700
Data Index: 388187 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.2888. Min Act: -0.1700
Data Index: 7098356 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.2575. Min Act: -0.1700
Data Index: 7758886 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.2263. Min Act: -0.1700
Data Index: 4974880 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.2263. Min Act: -0.1700
Data Index: 835311 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1950. Min Act: -0.1700
Data Index: 2178302 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1950. Min Act: -0.1700
Data Index: 335486 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1638. Min Act: -0.1700
Data Index: 6850744 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1638. Min Act: -0.1700
Data Index: 6440857 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1638. Min Act: -0.1700
Data Index: 6160323 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1638. Min Act: -0.1700
Data Index: 3922674 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1638. Min Act: -0.1700
Data Index: 6527909 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1638. Min Act: -0.1700
Data Index: 2331955 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1325. Min Act: -0.1700
Data Index: 2916662 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.1013. Min Act: -0.1700
Data Index: 5697030 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.0700. Min Act: -0.1700
Data Index: 8338278 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.0700. Min Act: -0.1700
Data Index: 971708 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.0700. Min Act: -0.1700
Data Index: 6078016 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5388. Min Range: -5.5388
Max Act: 5.0388. Min Act: -0.1700
Data Index: 2062436 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19