Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4236 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.7170. Min Act: -0.1699
Data Index: 87312 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.6530. Min Act: -0.1700
Data Index: 5770375 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.6369. Min Act: -0.1700
Data Index: 5985364 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5887. Min Act: -0.1700
Data Index: 5770380 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.6048. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.6369. Min Act: -0.1700
Data Index: 3852155 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.6048. Min Act: -0.1700
Data Index: 2898940 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.6048. Min Act: -0.1700
Data Index: 5770374 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.6048. Min Act: -0.1700
Data Index: 5770377 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5403. Min Act: -0.1700
Data Index: 3852156 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5564. Min Act: -0.1700
Data Index: 2717589 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5564. Min Act: -0.1700
Data Index: 1160739 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5725. Min Act: -0.1699
Data Index: 1804363 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5403. Min Act: -0.1700
Data Index: 1160740 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5241. Min Act: -0.1700
Data Index: 6171618 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5241. Min Act: -0.1700
Data Index: 5770379 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5241. Min Act: -0.1700
Data Index: 5770368 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5241. Min Act: -0.1700
Data Index: 3679703 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5241. Min Act: -0.1700
Data Index: 5770351 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7170. Min Range: -2.7170
Max Act: 2.5241. Min Act: -0.1700
Data Index: 5770366 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19