Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1054 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.4163. Min Act: -0.1700
Data Index: 4826247 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.2998. Min Act: -0.1700
Data Index: 1580837 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.3155. Min Act: -0.1700
Data Index: 6559166 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.2899. Min Act: -0.1700
Data Index: 2565712 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.2998. Min Act: -0.1700
Data Index: 7647705 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.2774. Min Act: -0.1700
Data Index: 1899799 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.2415. Min Act: -0.1700
Data Index: 4009363 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.2605. Min Act: -0.1700
Data Index: 1184097 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.2362. Min Act: -0.1700
Data Index: 7074674 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.2279. Min Act: -0.1700
Data Index: 4040390 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1653. Min Act: -0.1700
Data Index: 1806034 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1431. Min Act: -0.1700
Data Index: 5673447 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1363. Min Act: -0.1700
Data Index: 1296741 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1478. Min Act: -0.1700
Data Index: 8392111 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1436. Min Act: -0.1700
Data Index: 4476101 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1387. Min Act: -0.1700
Data Index: 2909853 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1243. Min Act: -0.1700
Data Index: 6519878 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1294. Min Act: -0.1700
Data Index: 6721733 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1185. Min Act: -0.1700
Data Index: 3164979 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.4163. Min Range: -3.4163
Max Act: 3.1423. Min Act: -0.1700
Data Index: 3092437 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full textTruncated
Full Text #19