Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 823 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.3364. Min Act: -0.1700
Data Index: 5040013 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.3052. Min Act: -0.1700
Data Index: 7724335 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2739. Min Act: -0.1700
Data Index: 2837206 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2739. Min Act: -0.1700
Data Index: 4061398 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2739. Min Act: -0.1700
Data Index: 601630 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2739. Min Act: -0.1700
Data Index: 5261466 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2739. Min Act: -0.1700
Data Index: 4459250 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2739. Min Act: -0.1700
Data Index: 4679363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2739. Min Act: -0.1700
Data Index: 4940268 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2427. Min Act: -0.1700
Data Index: 587147 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.2427. Min Act: -0.1700
Data Index: 7520023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.1802. Min Act: -0.1700
Data Index: 7879923 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.1802. Min Act: -0.1700
Data Index: 6721049 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.1489. Min Act: -0.1700
Data Index: 2442554 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.1177. Min Act: -0.1700
Data Index: 272988 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.1177. Min Act: -0.1700
Data Index: 6017634 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.0864. Min Act: -0.1700
Data Index: 23218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.0864. Min Act: -0.1700
Data Index: 5011219 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.0864. Min Act: -0.1700
Data Index: 2842871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3364. Min Range: -4.3364
Max Act: 4.0864. Min Act: -0.1700
Data Index: 2576596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19