Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.5393. Min Act: -0.1700
Data Index: 6380397 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.5393. Min Act: -0.1700
Data Index: 2347662 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.4456. Min Act: -0.1700
Data Index: 3633933 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.4456. Min Act: -0.1700
Data Index: 8217369 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.3831. Min Act: -0.1699
Data Index: 3762462 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.3206. Min Act: -0.1700
Data Index: 1349059 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.2893. Min Act: -0.1700
Data Index: 1426155 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.2581. Min Act: -0.1700
Data Index: 1222354 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.2893. Min Act: -0.1700
Data Index: 2532123 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.2581. Min Act: -0.1700
Data Index: 4719358 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.2268. Min Act: -0.1700
Data Index: 5286456 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.2268. Min Act: -0.1700
Data Index: 1438066 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.2268. Min Act: -0.1700
Data Index: 6752531 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.1956. Min Act: -0.1700
Data Index: 8454742 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.1643. Min Act: -0.1700
Data Index: 8416671 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.1956. Min Act: -0.1700
Data Index: 1486097 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.1956. Min Act: -0.1700
Data Index: 4212696 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.1956. Min Act: -0.1700
Data Index: 5857742 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.1643. Min Act: -0.1700
Data Index: 3682061 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.1643. Min Act: -0.1700
Data Index: 2591962 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19