Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0547. Min Range: -7.0547
Max Act: 7.0547. Min Act: -0.1700
Data Index: 2203404 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.8672. Min Act: -0.1700
Data Index: 7961259 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.8672. Min Act: -0.1700
Data Index: 3344907 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.7110. Min Act: -0.1700
Data Index: 3573343 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.6485. Min Act: -0.1700
Data Index: 6875668 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.6172. Min Act: -0.1700
Data Index: 1773901 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.5860. Min Act: -0.1700
Data Index: 7322876 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.5860. Min Act: -0.1700
Data Index: 2128402 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4610. Min Act: -0.1700
Data Index: 3912106 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4610. Min Act: -0.1700
Data Index: 8003302 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4610. Min Act: -0.1700
Data Index: 7702877 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4610. Min Act: -0.1700
Data Index: 4054818 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4922. Min Act: -0.1700
Data Index: 4842694 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4610. Min Act: -0.1700
Data Index: 2823846 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4610. Min Act: -0.1700
Data Index: 3745294 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4297. Min Act: -0.1700
Data Index: 6685841 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4297. Min Act: -0.1700
Data Index: 8003303 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4297. Min Act: -0.1700
Data Index: 6513116 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.4297. Min Act: -0.1700
Data Index: 4169506 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0547. Min Range: -7.0547
Max Act: 6.3985. Min Act: -0.1700
Data Index: 1613352 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19