Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4790 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3093. Min Range: -6.3093
Max Act: 6.3093. Min Act: -0.1700
Data Index: 2138014 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3093. Min Range: -6.3093
Max Act: 6.1530. Min Act: -0.1700
Data Index: 804594 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3093. Min Range: -6.3093
Max Act: 6.1530. Min Act: -0.1700
Data Index: 408932 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3093. Min Range: -6.3093
Max Act: 6.0905. Min Act: -0.1700
Data Index: 8824480 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3093. Min Range: -6.3093
Max Act: 6.0905. Min Act: -0.1700
Data Index: 2337971 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3093. Min Range: -6.3093
Max Act: 6.0593. Min Act: -0.1700
Data Index: 5990727 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3093. Min Range: -6.3093
Max Act: 6.0593. Min Act: -0.1700
Data Index: 4000160 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.9968. Min Act: -0.1700
Data Index: 4068724 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.9343. Min Act: -0.1700
Data Index: 4783512 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.9343. Min Act: -0.1700
Data Index: 6510741 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.9343. Min Act: -0.1700
Data Index: 8171680 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.9030. Min Act: -0.1700
Data Index: 8727364 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.9030. Min Act: -0.1700
Data Index: 7913527 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.8405. Min Act: -0.1700
Data Index: 5470280 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.8718. Min Act: -0.1700
Data Index: 719904 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.8718. Min Act: -0.1700
Data Index: 6999480 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.8718. Min Act: -0.1700
Data Index: 6740215 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.8718. Min Act: -0.1700
Data Index: 2761152 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.8093. Min Act: -0.1700
Data Index: 3123120 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3093. Min Range: -6.3093
Max Act: 5.8405. Min Act: -0.1700
Data Index: 7913517 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19