Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.2277. Min Act: -0.1700
Data Index: 8588147 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1652. Min Act: -0.1700
Data Index: 698951 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1027. Min Act: -0.1700
Data Index: 8588137 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0402. Min Act: -0.1700
Data Index: 4109228 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0402. Min Act: -0.1700
Data Index: 7063501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9777. Min Act: -0.1700
Data Index: 2672583 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9777. Min Act: -0.1700
Data Index: 8582760 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0089. Min Act: -0.1700
Data Index: 2632536 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9464. Min Act: -0.1700
Data Index: 5001409 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9151. Min Act: -0.1700
Data Index: 3649544 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9151. Min Act: -0.1700
Data Index: 5927830 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9151. Min Act: -0.1700
Data Index: 8675068 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8213. Min Act: -0.1700
Data Index: 2079414 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8213. Min Act: -0.1700
Data Index: 4052142 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8213. Min Act: -0.1700
Data Index: 2108422 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8213. Min Act: -0.1700
Data Index: 6943656 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8526. Min Act: -0.1700
Data Index: 7500784 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.7901. Min Act: -0.1700
Data Index: 6823290 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8213. Min Act: -0.1700
Data Index: 8342431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8213. Min Act: -0.1700
Data Index: 5810795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19