Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1571 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.4300. Min Act: -0.1700
Data Index: 3878468 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.3974. Min Act: -0.1700
Data Index: 6932506 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.3647. Min Act: -0.1700
Data Index: 1646961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2826. Min Act: -0.1700
Data Index: 1060975 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2990. Min Act: -0.1700
Data Index: 6538907 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2990. Min Act: -0.1700
Data Index: 1940736 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2826. Min Act: -0.1700
Data Index: 7190419 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2661. Min Act: -0.1700
Data Index: 4852022 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2496. Min Act: -0.1700
Data Index: 869782 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2661. Min Act: -0.1700
Data Index: 7559183 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2496. Min Act: -0.1700
Data Index: 2240769 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2661. Min Act: -0.1700
Data Index: 3224521 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2330. Min Act: -0.1700
Data Index: 5909646 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2330. Min Act: -0.1700
Data Index: 3476755 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2496. Min Act: -0.1700
Data Index: 7505073 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2330. Min Act: -0.1700
Data Index: 2680165 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2330. Min Act: -0.1700
Data Index: 3379268 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2330. Min Act: -0.1700
Data Index: 1906591 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2165. Min Act: -0.1700
Data Index: 1692565 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4300. Min Range: -2.4300
Max Act: 2.2330. Min Act: -0.1700
Data Index: 5388417 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19