Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 283 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2695. Min Range: -4.2695
Max Act: 4.2695. Min Act: -0.1700
Data Index: 157542 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.9570. Min Act: -0.1700
Data Index: 5374252 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.9570. Min Act: -0.1700
Data Index: 4723233 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.9257. Min Act: -0.1700
Data Index: 2705583 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8944. Min Act: -0.1700
Data Index: 6230471 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.9257. Min Act: -0.1700
Data Index: 399613 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8944. Min Act: -0.1700
Data Index: 2413394 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8788. Min Act: -0.1700
Data Index: 3534058 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8632. Min Act: -0.1700
Data Index: 6452601 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8632. Min Act: -0.1700
Data Index: 7661943 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8632. Min Act: -0.1700
Data Index: 5305959 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8475. Min Act: -0.1700
Data Index: 446606 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8475. Min Act: -0.1700
Data Index: 5390879 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8163. Min Act: -0.1700
Data Index: 1467623 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8319. Min Act: -0.1700
Data Index: 6053059 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8163. Min Act: -0.1700
Data Index: 649030 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8163. Min Act: -0.1700
Data Index: 1799858 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8006. Min Act: -0.1700
Data Index: 4723676 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.7850. Min Act: -0.1700
Data Index: 2919886 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2695. Min Range: -4.2695
Max Act: 3.8006. Min Act: -0.1700
Data Index: 513084 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19