Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4878 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4075. Min Range: -8.4075
Max Act: 8.4075. Min Act: -0.1700
Data Index: 4728147 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4075. Min Range: -8.4075
Max Act: 8.4075. Min Act: -0.1700
Data Index: 4354644 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4075. Min Range: -8.4075
Max Act: 8.2200. Min Act: -0.1700
Data Index: 4728149 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4075. Min Range: -8.4075
Max Act: 8.0638. Min Act: -0.1700
Data Index: 1529233 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.9700. Min Act: -0.1700
Data Index: 8569118 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.9700. Min Act: -0.1700
Data Index: 6766385 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.9388. Min Act: -0.1700
Data Index: 1529232 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.8763. Min Act: -0.1700
Data Index: 5744207 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.8450. Min Act: -0.1700
Data Index: 4728146 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.8138. Min Act: -0.1700
Data Index: 7969201 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.7825. Min Act: -0.1700
Data Index: 4354645 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.7825. Min Act: -0.1700
Data Index: 6548432 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.7200. Min Act: -0.1700
Data Index: 4961146 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.6888. Min Act: -0.1700
Data Index: 7968235 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.6575. Min Act: -0.1700
Data Index: 5585377 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.6263. Min Act: -0.1700
Data Index: 7759156 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.6263. Min Act: -0.1700
Data Index: 4728148 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.5950. Min Act: -0.1700
Data Index: 7394674 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.5638. Min Act: -0.1700
Data Index: 114224 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4075. Min Range: -8.4075
Max Act: 7.5950. Min Act: -0.1700
Data Index: 4243523 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19