Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 453 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.5059. Min Act: -0.1700
Data Index: 85650 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.4434. Min Act: -0.1700
Data Index: 4768413 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3809. Min Act: -0.1700
Data Index: 118554 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 2004163 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 8685245 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 7545508 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2246. Min Act: -0.1700
Data Index: 3420457 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2246. Min Act: -0.1700
Data Index: 4948649 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2559. Min Act: -0.1700
Data Index: 7245520 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2246. Min Act: -0.1700
Data Index: 2551543 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1933. Min Act: -0.1700
Data Index: 3473940 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1621. Min Act: -0.1700
Data Index: 2660645 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1933. Min Act: -0.1700
Data Index: 3759307 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1621. Min Act: -0.1700
Data Index: 6780928 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1308. Min Act: -0.1700
Data Index: 8312832 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.0996. Min Act: -0.1700
Data Index: 2578109 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1308. Min Act: -0.1700
Data Index: 3124656 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1308. Min Act: -0.1700
Data Index: 3942983 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1308. Min Act: -0.1700
Data Index: 1268153 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.1308. Min Act: -0.1700
Data Index: 7159739 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19