Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5355 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.3961. Min Act: -0.1700
Data Index: 237017 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.2711. Min Act: -0.1700
Data Index: 4132772 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.2086. Min Act: -0.1700
Data Index: 4022429 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.2086. Min Act: -0.1700
Data Index: 5654414 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.2086. Min Act: -0.1700
Data Index: 7003373 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.0836. Min Act: -0.1700
Data Index: 1491377 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.1461. Min Act: -0.1700
Data Index: 2943738 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.1461. Min Act: -0.1700
Data Index: 171419 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.3961. Min Range: -15.3961
Max Act: 15.0836. Min Act: -0.1699
Data Index: 996403 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.9586. Min Act: -0.1700
Data Index: 4048001 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.9586. Min Act: -0.1700
Data Index: 8470149 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.9586. Min Act: -0.1700
Data Index: 3527345 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.9586. Min Act: -0.1700
Data Index: 2980082 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.8961. Min Act: -0.1700
Data Index: 38193 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.8336. Min Act: -0.1700
Data Index: 6195007 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.8961. Min Act: -0.1700
Data Index: 982101 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.8961. Min Act: -0.1700
Data Index: 433521 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.8336. Min Act: -0.1700
Data Index: 1286202 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.8961. Min Act: -0.1700
Data Index: 2653688 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.3961. Min Range: -15.3961
Max Act: 14.8336. Min Act: -0.1700
Data Index: 2728380 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19