Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 474 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.7941. Min Act: -0.1700
Data Index: 6927893 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.8254. Min Act: -0.1700
Data Index: 8029754 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.8254. Min Act: -0.1700
Data Index: 2143120 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.7004. Min Act: -0.1700
Data Index: 1242300 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.7941. Min Act: -0.1700
Data Index: 5943036 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6379. Min Act: -0.1700
Data Index: 39820 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.7004. Min Act: -0.1700
Data Index: 7551546 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.7629. Min Act: -0.1700
Data Index: 678124 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.7004. Min Act: -0.1700
Data Index: 7664581 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.7004. Min Act: -0.1700
Data Index: 304876 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.7004. Min Act: -0.1700
Data Index: 6348962 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6691. Min Act: -0.1700
Data Index: 7792058 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6691. Min Act: -0.1700
Data Index: 4394415 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6691. Min Act: -0.1700
Data Index: 7978118 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6379. Min Act: -0.1680
Data Index: 1093876 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6691. Min Act: -0.1700
Data Index: 4922540 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6691. Min Act: -0.1700
Data Index: 5553254 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6691. Min Act: -0.1700
Data Index: 2474349 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6066. Min Act: -0.1700
Data Index: 6939950 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8254. Min Range: -4.8254
Max Act: 4.6066. Min Act: -0.1700
Data Index: 7341647 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19