Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5049 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.4494. Min Act: -0.1700
Data Index: 2325892 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2932. Min Act: -0.1700
Data Index: 8696505 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2932. Min Act: -0.1700
Data Index: 4414067 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2932. Min Act: -0.1700
Data Index: 7393743 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2619. Min Act: -0.1700
Data Index: 3526832 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2619. Min Act: -0.1700
Data Index: 235693 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2307. Min Act: -0.1700
Data Index: 7626584 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2619. Min Act: -0.1700
Data Index: 636207 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1994. Min Act: -0.1700
Data Index: 4955708 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1994. Min Act: -0.1700
Data Index: 7956211 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1994. Min Act: -0.1700
Data Index: 526987 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1994. Min Act: -0.1700
Data Index: 5588164 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1682. Min Act: -0.1700
Data Index: 615647 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1682. Min Act: -0.1700
Data Index: 847577 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1369. Min Act: -0.1700
Data Index: 3578742 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1369. Min Act: -0.1700
Data Index: 1738896 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1057. Min Act: -0.1700
Data Index: 245981 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1369. Min Act: -0.1700
Data Index: 8715863 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1057. Min Act: -0.1700
Data Index: 8769855 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1369. Min Act: -0.1700
Data Index: 4865092 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19