Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1886 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.1060. Min Range: -3.1060
Max Act: 3.1060. Min Act: -0.1700
Data Index: 118360 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9935. Min Act: -0.1700
Data Index: 3488347 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9668. Min Act: -0.1700
Data Index: 7031655 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9422. Min Act: -0.1700
Data Index: 5519396 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9331. Min Act: -0.1700
Data Index: 8452197 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9195. Min Act: -0.1700
Data Index: 560785 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8920. Min Act: -0.1700
Data Index: 5749534 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9120. Min Act: -0.1700
Data Index: 1265538 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9197. Min Act: -0.1700
Data Index: 2095322 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8734. Min Act: -0.1700
Data Index: 131904 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8226. Min Act: -0.1700
Data Index: 3139121 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8255. Min Act: -0.1700
Data Index: 8098857 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8278. Min Act: -0.1700
Data Index: 1003419 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8211. Min Act: -0.1700
Data Index: 6690453 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8203. Min Act: -0.1700
Data Index: 4010283 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8178. Min Act: -0.1700
Data Index: 3509181 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8196. Min Act: -0.1700
Data Index: 2948624 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8248. Min Act: -0.1700
Data Index: 4190938 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8265. Min Act: -0.1700
Data Index: 6153960 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7769. Min Act: -0.1700
Data Index: 3245136 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full textTruncated
Full Text #19