Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.5133. Min Act: -0.1700
Data Index: 3967246 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.4809. Min Act: -0.1700
Data Index: 6950445 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3669. Min Act: -0.1700
Data Index: 1924005 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3996. Min Act: -0.1700
Data Index: 613841 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3996. Min Act: -0.1700
Data Index: 2019603 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3832. Min Act: -0.1700
Data Index: 4592049 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3832. Min Act: -0.1700
Data Index: 4827741 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3832. Min Act: -0.1700
Data Index: 4554053 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3669. Min Act: -0.1700
Data Index: 8513178 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3505. Min Act: -0.1700
Data Index: 8608274 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3505. Min Act: -0.1700
Data Index: 7068561 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3341. Min Act: -0.1700
Data Index: 7335034 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3177. Min Act: -0.1700
Data Index: 5810556 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3177. Min Act: -0.1700
Data Index: 6754013 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3177. Min Act: -0.1700
Data Index: 6495179 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3013. Min Act: -0.1700
Data Index: 3193514 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3013. Min Act: -0.1700
Data Index: 1035904 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3013. Min Act: -0.1700
Data Index: 719620 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3013. Min Act: -0.1700
Data Index: 4827746 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5133. Min Range: -2.5133
Max Act: 2.3013. Min Act: -0.1700
Data Index: 2019602 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19