Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.6763. Min Act: -0.1700
Data Index: 7784986 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.5513. Min Act: -0.1700
Data Index: 3731219 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.5201. Min Act: -0.1700
Data Index: 4732723 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.5201. Min Act: -0.1700
Data Index: 2891788 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.5201. Min Act: -0.1700
Data Index: 7574754 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.4263. Min Act: -0.1700
Data Index: 2527451 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3638. Min Act: -0.1700
Data Index: 1755326 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3638. Min Act: -0.1700
Data Index: 3442621 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3638. Min Act: -0.1700
Data Index: 8743893 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3638. Min Act: -0.1700
Data Index: 1789623 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3638. Min Act: -0.1700
Data Index: 5541534 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3326. Min Act: -0.1700
Data Index: 6339495 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3326. Min Act: -0.1700
Data Index: 1970139 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3326. Min Act: -0.1700
Data Index: 6266904 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3013. Min Act: -0.1700
Data Index: 7837957 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3326. Min Act: -0.1700
Data Index: 8304646 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3326. Min Act: -0.1700
Data Index: 6201422 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3326. Min Act: -0.1700
Data Index: 8754825 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3326. Min Act: -0.1700
Data Index: 4468883 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6763. Min Range: -4.6763
Max Act: 4.3013. Min Act: -0.1700
Data Index: 3246139 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19