Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.3043. Min Act: -0.1700
Data Index: 678564 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2729. Min Act: -0.1700
Data Index: 331654 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2729. Min Act: -0.1700
Data Index: 6194102 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2258. Min Act: -0.1700
Data Index: 2571025 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2101. Min Act: -0.1700
Data Index: 6016665 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 4385154 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 4430826 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1786. Min Act: -0.1700
Data Index: 1943493 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 1310867 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1786. Min Act: -0.1700
Data Index: 4195649 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1629. Min Act: -0.1700
Data Index: 2995084 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1786. Min Act: -0.1700
Data Index: 5687193 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1629. Min Act: -0.1700
Data Index: 4881705 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1629. Min Act: -0.1700
Data Index: 8690539 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 6282292 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1629. Min Act: -0.1700
Data Index: 780968 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1629. Min Act: -0.1700
Data Index: 79654 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1629. Min Act: -0.1700
Data Index: 579297 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1629. Min Act: -0.1700
Data Index: 4719168 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1472. Min Act: -0.1700
Data Index: 3181981 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19