Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1474. Min Range: -6.1474
Max Act: 6.1474. Min Act: -0.1700
Data Index: 6931670 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.8661. Min Act: -0.1700
Data Index: 8325161 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.8974. Min Act: -0.1700
Data Index: 2588103 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.8349. Min Act: -0.1700
Data Index: 2127315 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.7724. Min Act: -0.1700
Data Index: 1103267 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.7411. Min Act: -0.1700
Data Index: 2912473 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.6786. Min Act: -0.1700
Data Index: 3608279 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.6786. Min Act: -0.1700
Data Index: 3019533 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.6474. Min Act: -0.1700
Data Index: 2934920 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.6474. Min Act: -0.1700
Data Index: 2560177 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.6474. Min Act: -0.1700
Data Index: 4284568 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.5849. Min Act: -0.1700
Data Index: 2187553 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.6161. Min Act: -0.1700
Data Index: 8112073 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.5849. Min Act: -0.1700
Data Index: 1288978 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.6161. Min Act: -0.1700
Data Index: 960964 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.6161. Min Act: -0.1700
Data Index: 5693950 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.5849. Min Act: -0.1700
Data Index: 5673053 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.5849. Min Act: -0.1700
Data Index: 88474 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.5849. Min Act: -0.1700
Data Index: 1610575 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1474. Min Range: -6.1474
Max Act: 5.5849. Min Act: -0.1700
Data Index: 6276097 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19