Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 944 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.1377. Min Act: -0.1700
Data Index: 5988016 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.1043. Min Act: -0.1700
Data Index: 5988017 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0875. Min Act: -0.1700
Data Index: 3967659 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0707. Min Act: -0.1700
Data Index: 6659147 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0371. Min Act: -0.1700
Data Index: 8515145 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0203. Min Act: -0.1700
Data Index: 4299333 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0203. Min Act: -0.1700
Data Index: 2479856 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0203. Min Act: -0.1700
Data Index: 4806187 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0034. Min Act: -0.1700
Data Index: 6901725 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0034. Min Act: -0.1700
Data Index: 3881084 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0034. Min Act: -0.1700
Data Index: 2301050 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1377. Min Range: -2.1377
Max Act: 2.0034. Min Act: -0.1700
Data Index: 1221231 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1377. Min Range: -2.1377
Max Act: 1.9865. Min Act: -0.1700
Data Index: 2681415 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1377. Min Range: -2.1377
Max Act: 1.9865. Min Act: -0.1700
Data Index: 2624974 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1377. Min Range: -2.1377
Max Act: 1.9865. Min Act: -0.1700
Data Index: 4962419 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1377. Min Range: -2.1377
Max Act: 1.9695. Min Act: -0.1700
Data Index: 6108205 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1377. Min Range: -2.1377
Max Act: 1.9695. Min Act: -0.1700
Data Index: 3419701 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1377. Min Range: -2.1377
Max Act: 1.9695. Min Act: -0.1700
Data Index: 502782 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1377. Min Range: -2.1377
Max Act: 1.9526. Min Act: -0.1700
Data Index: 3916654 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1377. Min Range: -2.1377
Max Act: 1.9695. Min Act: -0.1700
Data Index: 4196344 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19