Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4277 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.2524. Min Act: -0.1700
Data Index: 1573612 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.2194. Min Act: -0.1699
Data Index: 5258035 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.1695. Min Act: -0.1700
Data Index: 2754659 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.1195. Min Act: -0.1700
Data Index: 423823 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.1028. Min Act: -0.1700
Data Index: 4182286 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.1028. Min Act: -0.1698
Data Index: 5520811 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.1028. Min Act: -0.1700
Data Index: 3343262 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.1028. Min Act: -0.1700
Data Index: 8130679 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0860. Min Act: -0.1700
Data Index: 4932857 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0860. Min Act: -0.1700
Data Index: 432116 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0693. Min Act: -0.1700
Data Index: 2141766 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0693. Min Act: -0.1700
Data Index: 3343263 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0860. Min Act: -0.1700
Data Index: 1871158 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0693. Min Act: -0.1700
Data Index: 3564795 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0693. Min Act: -0.1700
Data Index: 147213 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0693. Min Act: -0.1700
Data Index: 1837104 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0693. Min Act: -0.1700
Data Index: 4039650 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0525. Min Act: -0.1700
Data Index: 3542429 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0693. Min Act: -0.1700
Data Index: 4932859 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2524. Min Range: -2.2524
Max Act: 2.0525. Min Act: -0.1700
Data Index: 5294654 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19