Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.4258. Min Act: -0.1700
Data Index: 241218 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2948. Min Act: -0.1700
Data Index: 6051357 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.3113. Min Act: -0.1700
Data Index: 5163573 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2784. Min Act: -0.1700
Data Index: 3163627 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.3113. Min Act: -0.1700
Data Index: 5859774 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2948. Min Act: -0.1700
Data Index: 4642972 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2784. Min Act: -0.1700
Data Index: 1871173 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2784. Min Act: -0.1700
Data Index: 4973222 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2619. Min Act: -0.1700
Data Index: 245012 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2619. Min Act: -0.1700
Data Index: 3163631 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2454. Min Act: -0.1700
Data Index: 458485 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2288. Min Act: -0.1700
Data Index: 4091838 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2288. Min Act: -0.1700
Data Index: 7790827 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2454. Min Act: -0.1700
Data Index: 8504763 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2123. Min Act: -0.1700
Data Index: 856242 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2288. Min Act: -0.1700
Data Index: 8418279 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.1957. Min Act: -0.1700
Data Index: 6999119 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2288. Min Act: -0.1700
Data Index: 6264353 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2123. Min Act: -0.1700
Data Index: 7352273 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4258. Min Range: -2.4258
Max Act: 2.2288. Min Act: -0.1700
Data Index: 8418278 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19