Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.3580. Min Act: -0.1700
Data Index: 6953906 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.2955. Min Act: -0.1700
Data Index: 1494330 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.2955. Min Act: -0.1700
Data Index: 2798003 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.2330. Min Act: -0.1700
Data Index: 5556652 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.2330. Min Act: -0.1700
Data Index: 6784258 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.1705. Min Act: -0.1700
Data Index: 5429952 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.1080. Min Act: -0.1700
Data Index: 1078636 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.1080. Min Act: -0.1700
Data Index: 8283950 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.0455. Min Act: -0.1700
Data Index: 8107462 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.0455. Min Act: -0.1700
Data Index: 2798004 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.0455. Min Act: -0.1700
Data Index: 665233 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.0455. Min Act: -0.1700
Data Index: 4266398 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.0455. Min Act: -0.1700
Data Index: 5964462 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.0455. Min Act: -0.1700
Data Index: 5080729 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3580. Min Range: -8.3580
Max Act: 8.1080. Min Act: -0.1700
Data Index: 7443415 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3580. Min Range: -8.3580
Max Act: 7.9830. Min Act: -0.1700
Data Index: 5483680 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3580. Min Range: -8.3580
Max Act: 7.9830. Min Act: -0.1700
Data Index: 3982109 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3580. Min Range: -8.3580
Max Act: 7.9830. Min Act: -0.1700
Data Index: 3448796 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3580. Min Range: -8.3580
Max Act: 7.9830. Min Act: -0.1700
Data Index: 7197042 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3580. Min Range: -8.3580
Max Act: 7.9830. Min Act: -0.1700
Data Index: 4518163 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19