Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 923 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.5487. Min Act: -0.1700
Data Index: 1653952 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.5487. Min Act: -0.1700
Data Index: 3330929 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.5174. Min Act: -0.1700
Data Index: 1398263 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4861. Min Act: -0.1700
Data Index: 4721328 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4861. Min Act: -0.1700
Data Index: 3036735 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4861. Min Act: -0.1700
Data Index: 1334756 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4861. Min Act: -0.1700
Data Index: 4770966 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4861. Min Act: -0.1700
Data Index: 6708480 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4861. Min Act: -0.1700
Data Index: 3962980 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4861. Min Act: -0.1700
Data Index: 3949039 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4861. Min Act: -0.1700
Data Index: 7959848 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4547. Min Act: -0.1700
Data Index: 4574142 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4547. Min Act: -0.1700
Data Index: 398124 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4547. Min Act: -0.1700
Data Index: 4770965 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4547. Min Act: -0.1700
Data Index: 3238383 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4547. Min Act: -0.1700
Data Index: 4967086 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4547. Min Act: -0.1700
Data Index: 5003040 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4547. Min Act: -0.1700
Data Index: 632048 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4234. Min Act: -0.1700
Data Index: 5623503 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5487. Min Range: -3.5487
Max Act: 3.4547. Min Act: -0.1700
Data Index: 1568894 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19