Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1111 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.7151. Min Act: -0.1700
Data Index: 3880095 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.4026. Min Act: -0.1700
Data Index: 6140548 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.3401. Min Act: -0.1700
Data Index: 7154380 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.3401. Min Act: -0.1700
Data Index: 4907035 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.2776. Min Act: -0.1700
Data Index: 1447809 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.2776. Min Act: -0.1700
Data Index: 1913444 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.2776. Min Act: -0.1700
Data Index: 7052047 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.2151. Min Act: -0.1700
Data Index: 5626974 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.2464. Min Act: -0.1700
Data Index: 1798791 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.2151. Min Act: -0.1700
Data Index: 6701361 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.1526. Min Act: -0.1700
Data Index: 7627890 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.1526. Min Act: -0.1700
Data Index: 1827703 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.1214. Min Act: -0.1700
Data Index: 2448625 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.0589. Min Act: -0.1700
Data Index: 7339940 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.0276. Min Act: -0.1700
Data Index: 1951992 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7151. Min Range: -8.7151
Max Act: 8.0276. Min Act: -0.1700
Data Index: 7506900 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7151. Min Range: -8.7151
Max Act: 7.9651. Min Act: -0.1700
Data Index: 804294 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7151. Min Range: -8.7151
Max Act: 7.9651. Min Act: -0.1700
Data Index: 6896147 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7151. Min Range: -8.7151
Max Act: 7.9651. Min Act: -0.1700
Data Index: 982098 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7151. Min Range: -8.7151
Max Act: 7.9651. Min Act: -0.1700
Data Index: 6575682 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19