Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2293 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.7133. Min Act: -0.1700
Data Index: 3338520 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5571. Min Act: -0.1700
Data Index: 8071669 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 5536987 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 1573884 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4946. Min Act: -0.1700
Data Index: 8122811 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 6919758 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 3798920 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 7354146 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 4262503 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 1557308 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4321. Min Act: -0.1700
Data Index: 7512079 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 4215743 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4321. Min Act: -0.1700
Data Index: 6604587 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4321. Min Act: -0.1700
Data Index: 1806177 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4321. Min Act: -0.1700
Data Index: 6289070 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 478872 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3696. Min Act: -0.1700
Data Index: 2295292 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 21609 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 640354 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 630355 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19