Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2542 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2904. Min Act: -0.1700
Data Index: 4995732 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2590. Min Act: -0.1700
Data Index: 3342991 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2433. Min Act: -0.1700
Data Index: 6576734 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2276. Min Act: -0.1700
Data Index: 8779156 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2433. Min Act: -0.1700
Data Index: 3637532 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1804. Min Act: -0.1700
Data Index: 386894 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2276. Min Act: -0.1700
Data Index: 1207542 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.2276. Min Act: -0.1700
Data Index: 2418734 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1174. Min Act: -0.1700
Data Index: 3505478 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1804. Min Act: -0.1700
Data Index: 4678674 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1647. Min Act: -0.1700
Data Index: 7596878 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1647. Min Act: -0.1700
Data Index: 8334311 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1489. Min Act: -0.1700
Data Index: 3570715 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1174. Min Act: -0.1700
Data Index: 7276505 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1332. Min Act: -0.1700
Data Index: 4387626 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1804. Min Act: -0.1700
Data Index: 766713 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.0859. Min Act: -0.1700
Data Index: 6034340 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1174. Min Act: -0.1700
Data Index: 2146547 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1174. Min Act: -0.1700
Data Index: 3339152 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2904. Min Range: -3.2904
Max Act: 3.1489. Min Act: -0.1700
Data Index: 429077 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19