Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.9230. Min Act: -0.1700
Data Index: 4298849 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.5480. Min Act: -0.1700
Data Index: 8609521 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.4855. Min Act: -0.1700
Data Index: 112239 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.4855. Min Act: -0.1700
Data Index: 1848802 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.4543. Min Act: -0.1700
Data Index: 6605076 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.3293. Min Act: -0.1700
Data Index: 7101599 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.3605. Min Act: -0.1700
Data Index: 3710163 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.3293. Min Act: -0.1700
Data Index: 8746095 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2668. Min Act: -0.1700
Data Index: 2104011 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2355. Min Act: -0.1700
Data Index: 8552342 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2668. Min Act: -0.1700
Data Index: 4469874 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2355. Min Act: -0.1700
Data Index: 820045 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2043. Min Act: -0.1700
Data Index: 7874590 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2355. Min Act: -0.1700
Data Index: 1238935 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2043. Min Act: -0.1700
Data Index: 5510365 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2043. Min Act: -0.1700
Data Index: 4917638 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2043. Min Act: -0.1700
Data Index: 2282823 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.2355. Min Act: -0.1700
Data Index: 5793772 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.1418. Min Act: -0.1700
Data Index: 2095635 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9230. Min Range: -6.9230
Max Act: 6.1418. Min Act: -0.1700
Data Index: 6007776 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19