Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.3833. Min Act: -0.1700
Data Index: 5574586 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.3208. Min Act: -0.1700
Data Index: 4192726 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.3208. Min Act: -0.1700
Data Index: 8036249 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.2583. Min Act: -0.1700
Data Index: 8478548 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.2270. Min Act: -0.1700
Data Index: 2236470 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.2270. Min Act: -0.1700
Data Index: 7896246 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1958. Min Act: -0.1700
Data Index: 6167740 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1645. Min Act: -0.1700
Data Index: 7896247 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1333. Min Act: -0.1700
Data Index: 1344961 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1333. Min Act: -0.1700
Data Index: 42835 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1333. Min Act: -0.1700
Data Index: 1062612 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1020. Min Act: -0.1700
Data Index: 4832787 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1020. Min Act: -0.1700
Data Index: 8343286 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1020. Min Act: -0.1700
Data Index: 3337904 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1020. Min Act: -0.1700
Data Index: 7599411 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1020. Min Act: -0.1700
Data Index: 4263928 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.1020. Min Act: -0.1700
Data Index: 2871923 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.0708. Min Act: -0.1700
Data Index: 323571 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.0708. Min Act: -0.1700
Data Index: 7497370 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3833. Min Range: -4.3833
Max Act: 4.0708. Min Act: -0.1700
Data Index: 2730145 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19