Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.3644. Min Act: -0.1700
Data Index: 3703091 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.3330. Min Act: -0.1700
Data Index: 4796005 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.2231. Min Act: -0.1700
Data Index: 5684629 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.2074. Min Act: -0.1700
Data Index: 3163222 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1916. Min Act: -0.1700
Data Index: 5915577 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1916. Min Act: -0.1700
Data Index: 3764938 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1916. Min Act: -0.1700
Data Index: 3764802 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1759. Min Act: -0.1700
Data Index: 5635735 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1759. Min Act: -0.1700
Data Index: 7726943 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1602. Min Act: -0.1700
Data Index: 7623712 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1602. Min Act: -0.1700
Data Index: 2054294 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1444. Min Act: -0.1700
Data Index: 4829937 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1444. Min Act: -0.1700
Data Index: 4676228 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1602. Min Act: -0.1700
Data Index: 2929465 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1444. Min Act: -0.1700
Data Index: 3955559 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1444. Min Act: -0.1700
Data Index: 3104292 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1287. Min Act: -0.1700
Data Index: 5583955 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1287. Min Act: -0.1700
Data Index: 703316 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1129. Min Act: -0.1700
Data Index: 6458559 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3644. Min Range: -3.3644
Max Act: 3.1129. Min Act: -0.1700
Data Index: 2279649 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19