Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.7837. Min Act: -0.1700
Data Index: 630530 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.7525. Min Act: -0.1700
Data Index: 32299 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.6275. Min Act: -0.1700
Data Index: 4430891 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.6587. Min Act: -0.1700
Data Index: 5631920 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.5650. Min Act: -0.1700
Data Index: 123685 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.5650. Min Act: -0.1700
Data Index: 950913 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.4400. Min Act: -0.1700
Data Index: 5582278 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.3150. Min Act: -0.1700
Data Index: 2402408 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.2837. Min Act: -0.1700
Data Index: 8389495 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.2525. Min Act: -0.1700
Data Index: 6967961 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.2525. Min Act: -0.1700
Data Index: 4868605 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.1900. Min Act: -0.1700
Data Index: 6914704 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.1275. Min Act: -0.1700
Data Index: 8636290 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.1275. Min Act: -0.1700
Data Index: 4588939 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.1587. Min Act: -0.1700
Data Index: 4162913 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.0962. Min Act: -0.1700
Data Index: 6725500 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.0337. Min Act: -0.1700
Data Index: 7114531 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7837. Min Range: -6.7837
Max Act: 5.9712. Min Act: -0.1700
Data Index: 4717406 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.0025. Min Act: -0.1700
Data Index: 5557225 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7837. Min Range: -6.7837
Max Act: 6.0025. Min Act: -0.1700
Data Index: 8230520 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19