Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.2195. Min Act: -0.1698
Data Index: 2292528 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1930. Min Act: -0.1700
Data Index: 7472436 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1754. Min Act: -0.1669
Data Index: 200350 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1491. Min Act: -0.1700
Data Index: 2133590 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1491. Min Act: -0.1700
Data Index: 7495983 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1578. Min Act: -0.1695
Data Index: 2310475 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1491. Min Act: -0.1697
Data Index: 2622211 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1491. Min Act: -0.1700
Data Index: 1159999 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1491. Min Act: -0.1699
Data Index: 4215345 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1403. Min Act: -0.1698
Data Index: 6117096 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1403. Min Act: -0.1692
Data Index: 6894616 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1491. Min Act: -0.1692
Data Index: 1576901 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1315. Min Act: -0.1696
Data Index: 184614 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1315. Min Act: -0.1675
Data Index: 58881 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1315. Min Act: -0.1696
Data Index: 2775763 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1315. Min Act: -0.1686
Data Index: 3441435 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1315. Min Act: -0.1696
Data Index: 7388223 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1227. Min Act: -0.1690
Data Index: 26380 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1140. Min Act: -0.1697
Data Index: 3424284 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2195. Min Range: -1.2195
Max Act: 1.1227. Min Act: -0.1697
Data Index: 6013103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19