Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 700 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.3234. Min Act: -0.1700
Data Index: 5760393 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.2906. Min Act: -0.1700
Data Index: 1510506 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.2741. Min Act: -0.1700
Data Index: 6892030 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.2576. Min Act: -0.1700
Data Index: 4135565 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.2576. Min Act: -0.1700
Data Index: 5741622 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.2411. Min Act: -0.1700
Data Index: 4045155 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.2079. Min Act: -0.1700
Data Index: 2884562 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1913. Min Act: -0.1700
Data Index: 6401174 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1747. Min Act: -0.1700
Data Index: 4501840 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.2079. Min Act: -0.1700
Data Index: 2141446 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1747. Min Act: -0.1700
Data Index: 8722819 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1747. Min Act: -0.1700
Data Index: 6709151 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1581. Min Act: -0.1700
Data Index: 7840693 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1581. Min Act: -0.1700
Data Index: 4273617 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1414. Min Act: -0.1700
Data Index: 8379316 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1414. Min Act: -0.1700
Data Index: 237942 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1080. Min Act: -0.1700
Data Index: 7242806 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1414. Min Act: -0.1700
Data Index: 4853455 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1414. Min Act: -0.1700
Data Index: 6004373 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3234. Min Range: -2.3234
Max Act: 2.1581. Min Act: -0.1700
Data Index: 7798076 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19