Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.8114. Min Act: -0.1700
Data Index: 3226519 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.6550. Min Act: -0.1700
Data Index: 8809902 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.5924. Min Act: -0.1700
Data Index: 912031 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.5768. Min Act: -0.1700
Data Index: 1537261 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.5924. Min Act: -0.1700
Data Index: 7558444 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.5141. Min Act: -0.1700
Data Index: 8135292 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4828. Min Act: -0.1700
Data Index: 1784786 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4515. Min Act: -0.1700
Data Index: 2758756 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4515. Min Act: -0.1700
Data Index: 2959736 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4515. Min Act: -0.1700
Data Index: 8596624 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4515. Min Act: -0.1700
Data Index: 3983363 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4358. Min Act: -0.1700
Data Index: 1749341 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4045. Min Act: -0.1700
Data Index: 7140773 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4045. Min Act: -0.1700
Data Index: 4013230 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4201. Min Act: -0.1700
Data Index: 5915995 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4045. Min Act: -0.1700
Data Index: 277831 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4045. Min Act: -0.1700
Data Index: 5965247 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4045. Min Act: -0.1700
Data Index: 2851468 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.4045. Min Act: -0.1700
Data Index: 1087701 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8114. Min Range: -3.8114
Max Act: 3.3574. Min Act: -0.1700
Data Index: 5965246 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19