Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1592 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.4144. Min Act: -0.1700
Data Index: 5636917 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.3206. Min Act: -0.1700
Data Index: 7541135 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.3206. Min Act: -0.1700
Data Index: 1926577 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2894. Min Act: -0.1700
Data Index: 5573908 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2581. Min Act: -0.1700
Data Index: 6457038 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2581. Min Act: -0.1700
Data Index: 2702969 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.2269. Min Act: -0.1700
Data Index: 8078028 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1956. Min Act: -0.1700
Data Index: 1169267 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1956. Min Act: -0.1700
Data Index: 6951648 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1956. Min Act: -0.1700
Data Index: 8202825 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1644. Min Act: -0.1700
Data Index: 3907658 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1956. Min Act: -0.1700
Data Index: 3959136 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1956. Min Act: -0.1700
Data Index: 5403186 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1644. Min Act: -0.1700
Data Index: 3454378 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1644. Min Act: -0.1700
Data Index: 4393951 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1644. Min Act: -0.1700
Data Index: 6011560 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1331. Min Act: -0.1700
Data Index: 2256740 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1019. Min Act: -0.1700
Data Index: 7766293 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1019. Min Act: -0.1700
Data Index: 6456103 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4144. Min Range: -6.4144
Max Act: 6.1019. Min Act: -0.1700
Data Index: 2552726 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19