Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1456 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.3454. Min Act: -0.1700
Data Index: 3675679 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.3297. Min Act: -0.1699
Data Index: 6616794 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.2983. Min Act: -0.1700
Data Index: 6188637 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.2983. Min Act: -0.1700
Data Index: 2937231 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.2512. Min Act: -0.1700
Data Index: 3685601 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.2512. Min Act: -0.1700
Data Index: 1368364 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.2355. Min Act: -0.1699
Data Index: 8282606 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.2041. Min Act: -0.1700
Data Index: 2669464 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1883. Min Act: -0.1700
Data Index: 8016901 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1726. Min Act: -0.1700
Data Index: 3842882 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1883. Min Act: -0.1700
Data Index: 7873340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1726. Min Act: -0.1700
Data Index: 1319803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1569. Min Act: -0.1700
Data Index: 5131463 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1569. Min Act: -0.1700
Data Index: 7417288 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1411. Min Act: -0.1700
Data Index: 8400734 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1411. Min Act: -0.1700
Data Index: 2347189 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1411. Min Act: -0.1700
Data Index: 2274762 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1411. Min Act: -0.1700
Data Index: 3847750 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1254. Min Act: -0.1700
Data Index: 8558061 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3454. Min Range: -3.3454
Max Act: 3.1096. Min Act: -0.1700
Data Index: 1759727 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19