Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2163. Min Range: -7.2163
Max Act: 7.2163. Min Act: -0.1700
Data Index: 3149640 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.9975. Min Act: -0.1700
Data Index: 1375542 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.8725. Min Act: -0.1700
Data Index: 260843 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.8413. Min Act: -0.1700
Data Index: 2430260 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.7788. Min Act: -0.1700
Data Index: 623232 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.8413. Min Act: -0.1700
Data Index: 7892952 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.6850. Min Act: -0.1700
Data Index: 8051355 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.6225. Min Act: -0.1700
Data Index: 6340347 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.5913. Min Act: -0.1700
Data Index: 4698828 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.5913. Min Act: -0.1700
Data Index: 565114 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.5913. Min Act: -0.1700
Data Index: 5758346 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.5600. Min Act: -0.1700
Data Index: 8172466 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.5288. Min Act: -0.1700
Data Index: 2762261 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.5288. Min Act: -0.1700
Data Index: 7465337 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.5600. Min Act: -0.1700
Data Index: 3980023 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.4975. Min Act: -0.1700
Data Index: 3210005 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.4975. Min Act: -0.1700
Data Index: 3663904 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.4663. Min Act: -0.1700
Data Index: 1158318 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.4350. Min Act: -0.1700
Data Index: 6294075 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2163. Min Range: -7.2163
Max Act: 6.4663. Min Act: -0.1700
Data Index: 5072966 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19