Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.4261. Min Act: -0.1700
Data Index: 1204622 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3636. Min Act: -0.1700
Data Index: 5260174 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3324. Min Act: -0.1700
Data Index: 4862141 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3636. Min Act: -0.1700
Data Index: 203201 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3324. Min Act: -0.1700
Data Index: 6189073 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3324. Min Act: -0.1700
Data Index: 6131246 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3636. Min Act: -0.1700
Data Index: 569549 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3011. Min Act: -0.1700
Data Index: 2942281 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3011. Min Act: -0.1700
Data Index: 3465232 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3324. Min Act: -0.1700
Data Index: 6993759 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.3011. Min Act: -0.1700
Data Index: 8395482 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2699. Min Act: -0.1700
Data Index: 2727006 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2699. Min Act: -0.1700
Data Index: 4232708 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2699. Min Act: -0.1700
Data Index: 1677768 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2386. Min Act: -0.1700
Data Index: 4413040 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2699. Min Act: -0.1700
Data Index: 283656 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2386. Min Act: -0.1700
Data Index: 8396564 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2386. Min Act: -0.1700
Data Index: 8191568 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2699. Min Act: -0.1700
Data Index: 2311825 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4261. Min Range: -4.4261
Max Act: 4.2074. Min Act: -0.1700
Data Index: 3174742 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19