Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2858 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4337. Min Act: -0.1700
Data Index: 5449170 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4337. Min Act: -0.1700
Data Index: 1470497 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4249. Min Act: -0.1700
Data Index: 6426836 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4337. Min Act: -0.1699
Data Index: 2716621 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4249. Min Act: -0.1700
Data Index: 1721389 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4161. Min Act: -0.1700
Data Index: 3497547 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4073. Min Act: -0.1700
Data Index: 4294387 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4161. Min Act: -0.1700
Data Index: 5095785 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.4073. Min Act: -0.1700
Data Index: 6834749 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3985. Min Act: -0.1700
Data Index: 7575465 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3985. Min Act: -0.1700
Data Index: 5065178 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3897. Min Act: -0.1700
Data Index: 2979558 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3897. Min Act: -0.1700
Data Index: 4033216 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3897. Min Act: -0.1699
Data Index: 4435134 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3985. Min Act: -0.1686
Data Index: 5113513 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3809. Min Act: -0.1700
Data Index: 4383706 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3897. Min Act: -0.1700
Data Index: 741395 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3809. Min Act: -0.1680
Data Index: 4252026 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3897. Min Act: -0.1699
Data Index: 3101765 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4337. Min Range: -1.4337
Max Act: 1.3897. Min Act: -0.1700
Data Index: 5445052 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19