Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2189 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3006. Min Range: -10.3006
Max Act: 10.3006. Min Act: -0.1700
Data Index: 1020191 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3006. Min Range: -10.3006
Max Act: 10.2381. Min Act: -0.1700
Data Index: 2555251 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3006. Min Range: -10.3006
Max Act: 10.0506. Min Act: -0.1700
Data Index: 2555247 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3006. Min Range: -10.3006
Max Act: 10.1131. Min Act: -0.1700
Data Index: 5689538 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3006. Min Range: -10.3006
Max Act: 10.1756. Min Act: -0.1700
Data Index: 4795534 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3006. Min Range: -10.3006
Max Act: 10.0506. Min Act: -0.1700
Data Index: 2555231 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3006. Min Range: -10.3006
Max Act: 10.1131. Min Act: -0.1700
Data Index: 3536954 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3006. Min Range: -10.3006
Max Act: 10.0506. Min Act: -0.1700
Data Index: 1020185 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9881. Min Act: -0.1700
Data Index: 8504036 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9881. Min Act: -0.1700
Data Index: 2555238 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9881. Min Act: -0.1700
Data Index: 2555246 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9881. Min Act: -0.1700
Data Index: 2555245 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9881. Min Act: -0.1700
Data Index: 8084318 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9256. Min Act: -0.1700
Data Index: 2555224 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9256. Min Act: -0.1700
Data Index: 2555226 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9256. Min Act: -0.1700
Data Index: 7786951 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.8631. Min Act: -0.1700
Data Index: 2555222 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9256. Min Act: -0.1700
Data Index: 6267969 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9256. Min Act: -0.1700
Data Index: 2773461 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3006. Min Range: -10.3006
Max Act: 9.9256. Min Act: -0.1700
Data Index: 2555235 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19